Yusser/CC-LARD

---
language:
- multilingual
license: cc-by-4.0
task_categories:
- text-generation
- text-classification
tags:
- common-crawl
- multilingual
- regional-corpus
- geographic
size_categories:
- 10M<n<100M
configs:
- config_name: "af-AF"
data_files:
- split: train
path: "data/af-AF/*.parquet"
- config_name: "af-BR"
data_files:
- split: train
path: "data/af-BR/*.parquet"
- config_name: "af-CO"
data_files:
- split: train
path: "data/af-CO/*.parquet"
- config_name: "af-CZ"
data_files:
- split: train
path: "data/af-CZ/*.parquet"
- config_name: "af-ES"
data_files:
- split: train
path: "data/af-ES/*.parquet"
- config_name: "af-GB"
data_files:
- split: train
path: "data/af-GB/*.parquet"
- config_name: "af-IT"
data_files:
- split: train
path: "data/af-IT/*.parquet"
- config_name: "af-NA"
data_files:
- split: train
path: "data/af-NA/*.parquet"
- config_name: "af-NL"
data_files:
- split: train
path: "data/af-NL/*.parquet"
- config_name: "af-NU"
data_files:
- split: train
path: "data/af-NU/*.parquet"
- config_name: "af-RU"
data_files:
- split: train
path: "data/af-RU/*.parquet"
- config_name: "af-SA"
data_files:
- split: train
path: "data/af-SA/*.parquet"
- config_name: "af-TK"
data_files:
- split: train
path: "data/af-TK/*.parquet"
- config_name: "af-US"
data_files:
- split: train
path: "data/af-US/*.parquet"
- config_name: "af-VN"
data_files:
- split: train
path: "data/af-VN/*.parquet"
- config_name: "af-WS"
data_files:
- split: train
path: "data/af-WS/*.parquet"
- config_name: "af-XX"
data_files:
- split: train
path: "data/af-XX/*.parquet"
- config_name: "af-ZA"
data_files:
- split: train
path: "data/af-ZA/*.parquet"
- config_name: "als-DE"
data_files:
- split: train
path: "data/als-DE/*.parquet"
- config_name: "als-GB"
data_files:
- split: train
path: "data/als-GB/*.parquet"
- config_name: "als-IT"
data_files:
- split: train
path: "data/als-IT/*.parquet"
- config_name: "als-US"
data_files:
- split: train
path: "data/als-US/*.parquet"
- config_name: "als-XX"
data_files:
- split: train
path: "data/als-XX/*.parquet"
- config_name: "am-AM"
data_files:
- split: train
path: "data/am-AM/*.parquet"
- config_name: "am-CA"
data_files:
- split: train
path: "data/am-CA/*.parquet"
- config_name: "am-CC"
data_files:
- split: train
path: "data/am-CC/*.parquet"
- config_name: "am-DE"
data_files:
- split: train
path: "data/am-DE/*.parquet"
- config_name: "am-ET"
data_files:
- split: train
path: "data/am-ET/*.parquet"
- config_name: "am-FI"
data_files:
- split: train
path: "data/am-FI/*.parquet"
- config_name: "am-FR"
data_files:
- split: train
path: "data/am-FR/*.parquet"
- config_name: "am-GB"
data_files:
- split: train
path: "data/am-GB/*.parquet"
- config_name: "am-NL"
data_files:
- split: train
path: "data/am-NL/*.parquet"
- config_name: "am-PL"
data_files:
- split: train
path: "data/am-PL/*.parquet"
- config_name: "am-SE"
data_files:
- split: train
path: "data/am-SE/*.parquet"
- config_name: "am-TI"
data_files:
- split: train
path: "data/am-TI/*.parquet"
- config_name: "am-US"
data_files:
- split: train
path: "data/am-US/*.parquet"
- config_name: "am-VA"
data_files:
- split: train
path: "data/am-VA/*.parquet"
- config_name: "am-VN"
data_files:
- split: train
path: "data/am-VN/*.parquet"
- config_name: "am-XX"
data_files:
- split: train
path: "data/am-XX/*.parquet"
- config_name: "an-XX"
data_files:
- split: train
path: "data/an-XX/*.parquet"
- config_name: "ar-AA"
data_files:
- split: train
path: "data/ar-AA/*.parquet"
- config_name: "ar-AB"
data_files:
- split: train
path: "data/ar-AB/*.parquet"
- config_name: "ar-AE"
data_files:
- split: train
path: "data/ar-AE/*.parquet"
- config_name: "ar-AF"
data_files:
- split: train
path: "data/ar-AF/*.parquet"
- config_name: "ar-AI"
data_files:
- split: train
path: "data/ar-AI/*.parquet"
- config_name: "ar-AL"
data_files:
- split: train
path: "data/ar-AL/*.parquet"
- config_name: "ar-AM"
data_files:
- split: train
path: "data/ar-AM/*.parquet"
- config_name: "ar-AR"
data_files:
- split: train
path: "data/ar-AR/*.parquet"
- config_name: "ar-AS"
data_files:
- split: train
path: "data/ar-AS/*.parquet"
- config_name: "ar-AT"
data_files:
- split: train
path: "data/ar-AT/*.parquet"
- config_name: "ar-AU"
data_files:
- split: train
path: "data/ar-AU/*.parquet"
- config_name: "ar-AZ"
data_files:
- split: train
path: "data/ar-AZ/*.parquet"
- config_name: "ar-BE"
data_files:
- split: train
path: "data/ar-BE/*.parquet"
- config_name: "ar-BH"
data_files:
- split: train
path: "data/ar-BH/*.parquet"
- config_name: "ar-BR"
data_files:
- split: train
path: "data/ar-BR/*.parquet"
- config_name: "ar-BZ"
data_files:
- split: train
path: "data/ar-BZ/*.parquet"
- config_name: "ar-CA"
data_files:
- split: train
path: "data/ar-CA/*.parquet"
- config_name: "ar-CC"
data_files:
- split: train
path: "data/ar-CC/*.parquet"
- config_name: "ar-CF"
data_files:
- split: train
path: "data/ar-CF/*.parquet"
- config_name: "ar-CH"
data_files:
- split: train
path: "data/ar-CH/*.parquet"
- config_name: "ar-CL"
data_files:
- split: train
path: "data/ar-CL/*.parquet"
- config_name: "ar-CN"
data_files:
- split: train
path: "data/ar-CN/*.parquet"
- config_name: "ar-CO"
data_files:
- split: train
path: "data/ar-CO/*.parquet"
- config_name: "ar-CU"
data_files:
- split: train
path: "data/ar-CU/*.parquet"
- config_name: "ar-CZ"
data_files:
- split: train
path: "data/ar-CZ/*.parquet"
- config_name: "ar-DE"
data_files:
- split: train
path: "data/ar-DE/*.parquet"
- config_name: "ar-DJ"
data_files:
- split: train
path: "data/ar-DJ/*.parquet"
- config_name: "ar-DK"
data_files:
- split: train
path: "data/ar-DK/*.parquet"
- config_name: "ar-DZ"
data_files:
- split: train
path: "data/ar-DZ/*.parquet"
- config_name: "ar-EG"
data_files:
- split: train
path: "data/ar-EG/*.parquet"
- config_name: "ar-EN"
data_files:
- split: train
path: "data/ar-EN/*.parquet"
- config_name: "ar-ES"
data_files:
- split: train
path: "data/ar-ES/*.parquet"
- config_name: "ar-EU"
data_files:
- split: train
path: "data/ar-EU/*.parquet"
- config_name: "ar-FI"
data_files:
- split: train
path: "data/ar-FI/*.parquet"
- config_name: "ar-FM"
data_files:
- split: train
path: "data/ar-FM/*.parquet"
- config_name: "ar-FR"
data_files:
- split: train
path: "data/ar-FR/*.parquet"
- config_name: "ar-GB"
data_files:
- split: train
path: "data/ar-GB/*.parquet"
- config_name: "ar-GG"
data_files:
- split: train
path: "data/ar-GG/*.parquet"
- config_name: "ar-GP"
data_files:
- split: train
path: "data/ar-GP/*.parquet"
- config_name: "ar-GR"
data_files:
- split: train
path: "data/ar-GR/*.parquet"
- config_name: "ar-HK"
data_files:
- split: train
path: "data/ar-HK/*.parquet"
- config_name: "ar-HR"
data_files:
- split: train
path: "data/ar-HR/*.parquet"
- config_name: "ar-HT"
data_files:
- split: train
path: "data/ar-HT/*.parquet"
- config_name: "ar-ID"
data_files:
- split: train
path: "data/ar-ID/*.parquet"
- config_name: "ar-IE"
data_files:
- split: train
path: "data/ar-IE/*.parquet"
- config_name: "ar-IL"
data_files:
- split: train
path: "data/ar-IL/*.parquet"
- config_name: "ar-IM"
data_files:
- split: train
path: "data/ar-IM/*.parquet"
- config_name: "ar-IN"
data_files:
- split: train
path: "data/ar-IN/*.parquet"
- config_name: "ar-IO"
data_files:
- split: train
path: "data/ar-IO/*.parquet"
- config_name: "ar-IQ"
data_files:
- split: train
path: "data/ar-IQ/*.parquet"
- config_name: "ar-IR"
data_files:
- split: train
path: "data/ar-IR/*.parquet"
- config_name: "ar-IS"
data_files:
- split: train
path: "data/ar-IS/*.parquet"
- config_name: "ar-IT"
data_files:
- split: train
path: "data/ar-IT/*.parquet"
- config_name: "ar-JO"
data_files:
- split: train
path: "data/ar-JO/*.parquet"
- config_name: "ar-JP"
data_files:
- split: train
path: "data/ar-JP/*.parquet"
- config_name: "ar-KI"
data_files:
- split: train
path: "data/ar-KI/*.parquet"
- config_name: "ar-KM"
data_files:
- split: train
path: "data/ar-KM/*.parquet"
- config_name: "ar-KR"
data_files:
- split: train
path: "data/ar-KR/*.parquet"
- config_name: "ar-KW"
data_files:
- split: train
path: "data/ar-KW/*.parquet"
- config_name: "ar-KZ"
data_files:
- split: train
path: "data/ar-KZ/*.parquet"
- config_name: "ar-LA"
data_files:
- split: train
path: "data/ar-LA/*.parquet"
- config_name: "ar-LB"
data_files:
- split: train
path: "data/ar-LB/*.parquet"
- config_name: "ar-LI"
data_files:
- split: train
path: "data/ar-LI/*.parquet"
- config_name: "ar-LT"
data_files:
- split: train
path: "data/ar-LT/*.parquet"
- config_name: "ar-LV"
data_files:
- split: train
path: "data/ar-LV/*.parquet"
- config_name: "ar-LY"
data_files:
- split: train
path: "data/ar-LY/*.parquet"
- config_name: "ar-MA"
data_files:
- split: train
path: "data/ar-MA/*.parquet"
- config_name: "ar-ME"
data_files:
- split: train
path: "data/ar-ME/*.parquet"
- config_name: "ar-ML"
data_files:
- split: train
path: "data/ar-ML/*.parquet"
- config_name: "ar-MP"
data_files:
- split: train
path: "data/ar-MP/*.parquet"
- config_name: "ar-MR"
data_files:
- split: train
path: "data/ar-MR/*.parquet"
- config_name: "ar-MX"
data_files:
- split: train
path: "data/ar-MX/*.parquet"
- config_name: "ar-MY"
data_files:
- split: train
path: "data/ar-MY/*.parquet"
- config_name: "ar-NA"
data_files:
- split: train
path: "data/ar-NA/*.parquet"
- config_name: "ar-NG"
data_files:
- split: train
path: "data/ar-NG/*.parquet"
- config_name: "ar-NL"
data_files:
- split: train
path: "data/ar-NL/*.parquet"
- config_name: "ar-NO"
data_files:
- split: train
path: "data/ar-NO/*.parquet"
- config_name: "ar-NU"
data_files:
- split: train
path: "data/ar-NU/*.parquet"
- config_name: "ar-NZ"
data_files:
- split: train
path: "data/ar-NZ/*.parquet"
- config_name: "ar-OM"
data_files:
- split: train
path: "data/ar-OM/*.parquet"
- config_name: "ar-PE"
data_files:
- split: train
path: "data/ar-PE/*.parquet"
- config_name: "ar-PK"
data_files:
- split: train
path: "data/ar-PK/*.parquet"
- config_name: "ar-PL"
data_files:
- split: train
path: "data/ar-PL/*.parquet"
- config_name: "ar-PS"
data_files:
- split: train
path: "data/ar-PS/*.parquet"
- config_name: "ar-PT"
data_files:
- split: train
path: "data/ar-PT/*.parquet"
- config_name: "ar-PW"
data_files:
- split: train
path: "data/ar-PW/*.parquet"
- config_name: "ar-QA"
data_files:
- split: train
path: "data/ar-QA/*.parquet"
- config_name: "ar-RO"
data_files:
- split: train
path: "data/ar-RO/*.parquet"
- config_name: "ar-RS"
data_files:
- split: train
path: "data/ar-RS/*.parquet"
- config_name: "ar-RU"
data_files:
- split: train
path: "data/ar-RU/*.parquet"
- config_name: "ar-SA"
data_files:
- split: train
path: "data/ar-SA/*.parquet"
- config_name: "ar-SC"
data_files:
- split: train
path: "data/ar-SC/*.parquet"
- config_name: "ar-SD"
data_files:
- split: train
path: "data/ar-SD/*.parquet"
- config_name: "ar-SE"
data_files:
- split: train
path: "data/ar-SE/*.parquet"
- config_name: "ar-SG"
data_files:
- split: train
path: "data/ar-SG/*.parquet"
- config_name: "ar-SH"
data_files:
- split: train
path: "data/ar-SH/*.parquet"
- config_name: "ar-SI"
data_files:
- split: train
path: "data/ar-SI/*.parquet"
- config_name: "ar-SK"
data_files:
- split: train
path: "data/ar-SK/*.parquet"
- config_name: "ar-SN"
data_files:
- split: train
path: "data/ar-SN/*.parquet"
- config_name: "ar-SO"
data_files:
- split: train
path: "data/ar-SO/*.parquet"
- config_name: "ar-ST"
data_files:
- split: train
path: "data/ar-ST/*.parquet"
- config_name: "ar-SX"
data_files:
- split: train
path: "data/ar-SX/*.parquet"
- config_name: "ar-SY"
data_files:
- split: train
path: "data/ar-SY/*.parquet"
- config_name: "ar-TC"
data_files:
- split: train
path: "data/ar-TC/*.parquet"
- config_name: "ar-TD"
data_files:
- split: train
path: "data/ar-TD/*.parquet"
- config_name: "ar-TH"
data_files:
- split: train
path: "data/ar-TH/*.parquet"
- config_name: "ar-TK"
data_files:
- split: train
path: "data/ar-TK/*.parquet"
- config_name: "ar-TL"
data_files:
- split: train
path: "data/ar-TL/*.parquet"
- config_name: "ar-TM"
data_files:
- split: train
path: "data/ar-TM/*.parquet"
- config_name: "ar-TN"
data_files:
- split: train
path: "data/ar-TN/*.parquet"
- config_name: "ar-TO"
data_files:
- split: train
path: "data/ar-TO/*.parquet"
- config_name: "ar-TR"
data_files:
- split: train
path: "data/ar-TR/*.parquet"
- config_name: "ar-TT"
data_files:
- split: train
path: "data/ar-TT/*.parquet"
- config_name: "ar-TV"
data_files:
- split: train
path: "data/ar-TV/*.parquet"
- config_name: "ar-TW"
data_files:
- split: train
path: "data/ar-TW/*.parquet"
- config_name: "ar-UA"
data_files:
- split: train
path: "data/ar-UA/*.parquet"
- config_name: "ar-US"
data_files:
- split: train
path: "data/ar-US/*.parquet"
- config_name: "ar-UZ"
data_files:
- split: train
path: "data/ar-UZ/*.parquet"
- config_name: "ar-VA"
data_files:
- split: train
path: "data/ar-VA/*.parquet"
- config_name: "ar-VN"
data_files:
- split: train
path: "data/ar-VN/*.parquet"
- config_name: "ar-VU"
data_files:
- split: train
path: "data/ar-VU/*.parquet"
- config_name: "ar-WS"
data_files:
- split: train
path: "data/ar-WS/*.parquet"
- config_name: "ar-WW"
data_files:
- split: train
path: "data/ar-WW/*.parquet"
- config_name: "ar-XA"
data_files:
- split: train
path: "data/ar-XA/*.parquet"
- config_name: "ar-XM"
data_files:
- split: train
path: "data/ar-XM/*.parquet"
- config_name: "ar-XX"
data_files:
- split: train
path: "data/ar-XX/*.parquet"
- config_name: "ar-YE"
data_files:
- split: train
path: "data/ar-YE/*.parquet"
- config_name: "ar-ZA"
data_files:
- split: train
path: "data/ar-ZA/*.parquet"
- config_name: "arz-AR"
data_files:
- split: train
path: "data/arz-AR/*.parquet"
- config_name: "arz-EG"
data_files:
- split: train
path: "data/arz-EG/*.parquet"
- config_name: "arz-RU"
data_files:
- split: train
path: "data/arz-RU/*.parquet"
- config_name: "arz-ST"
data_files:
- split: train
path: "data/arz-ST/*.parquet"
- config_name: "arz-US"
data_files:
- split: train
path: "data/arz-US/*.parquet"
- config_name: "arz-XX"
data_files:
- split: train
path: "data/arz-XX/*.parquet"
- config_name: "as-US"
data_files:
- split: train
path: "data/as-US/*.parquet"
- config_name: "as-XX"
data_files:
- split: train
path: "data/as-XX/*.parquet"
- config_name: "ast-XX"
data_files:
- split: train
path: "data/ast-XX/*.parquet"
- config_name: "av-XX"
data_files:
- split: train
path: "data/av-XX/*.parquet"
- config_name: "az-AL"
data_files:
- split: train
path: "data/az-AL/*.parquet"
- config_name: "az-AR"
data_files:
- split: train
path: "data/az-AR/*.parquet"
- config_name: "az-AT"
data_files:
- split: train
path: "data/az-AT/*.parquet"
- config_name: "az-AU"
data_files:
- split: train
path: "data/az-AU/*.parquet"
- config_name: "az-AZ"
data_files:
- split: train
path: "data/az-AZ/*.parquet"
- config_name: "az-BA"
data_files:
- split: train
path: "data/az-BA/*.parquet"
- config_name: "az-BR"
data_files:
- split: train
path: "data/az-BR/*.parquet"
- config_name: "az-CA"
data_files:
- split: train
path: "data/az-CA/*.parquet"
- config_name: "az-CH"
data_files:
- split: train
path: "data/az-CH/*.parquet"
- config_name: "az-CL"
data_files:
- split: train
path: "data/az-CL/*.parquet"
- config_name: "az-CO"
data_files:
- split: train
path: "data/az-CO/*.parquet"
- config_name: "az-CZ"
data_files:
- split: train
path: "data/az-CZ/*.parquet"
- config_name: "az-DE"
data_files:
- split: train
path: "data/az-DE/*.parquet"
- config_name: "az-DO"
data_files:
- split: train
path: "data/az-DO/*.parquet"
- config_name: "az-EG"
data_files:
- split: train
path: "data/az-EG/*.parquet"
- config_name: "az-ES"
data_files:
- split: train
path: "data/az-ES/*.parquet"
- config_name: "az-EU"
data_files:
- split: train
path: "data/az-EU/*.parquet"
- config_name: "az-FM"
data_files:
- split: train
path: "data/az-FM/*.parquet"
- config_name: "az-FR"
data_files:
- split: train
path: "data/az-FR/*.parquet"
- config_name: "az-GB"
data_files:
- split: train
path: "data/az-GB/*.parquet"
- config_name: "az-GE"
data_files:
- split: train
path: "data/az-GE/*.parquet"
- config_name: "az-GR"
data_files:
- split: train
path: "data/az-GR/*.parquet"
- config_name: "az-HR"
data_files:
- split: train
path: "data/az-HR/*.parquet"
- config_name: "az-HU"
data_files:
- split: train
path: "data/az-HU/*.parquet"
- config_name: "az-ID"
data_files:
- split: train
path: "data/az-ID/*.parquet"
- config_name: "az-IL"
data_files:
- split: train
path: "data/az-IL/*.parquet"
- config_name: "az-IN"
data_files:
- split: train
path: "data/az-IN/*.parquet"
- config_name: "az-IO"
data_files:
- split: train
path: "data/az-IO/*.parquet"
- config_name: "az-IR"
data_files:
- split: train
path: "data/az-IR/*.parquet"
- config_name: "az-IS"
data_files:
- split: train
path: "data/az-IS/*.parquet"
- config_name: "az-IT"
data_files:
- split: train
path: "data/az-IT/*.parquet"
- config_name: "az-JP"
data_files:
- split: train
path: "data/az-JP/*.parquet"
- config_name: "az-KR"
data_files:
- split: train
path: "data/az-KR/*.parquet"
- config_name: "az-KZ"
data_files:
- split: train
path: "data/az-KZ/*.parquet"
- config_name: "az-ME"
data_files:
- split: train
path: "data/az-ME/*.parquet"
- config_name: "az-MX"
data_files:
- split: train
path: "data/az-MX/*.parquet"
- config_name: "az-NL"
data_files:
- split: train
path: "data/az-NL/*.parquet"
- config_name: "az-PE"
data_files:
- split: train
path: "data/az-PE/*.parquet"
- config_name: "az-PL"
data_files:
- split: train
path: "data/az-PL/*.parquet"
- config_name: "az-PM"
data_files:
- split: train
path: "data/az-PM/*.parquet"
- config_name: "az-PT"
data_files:
- split: train
path: "data/az-PT/*.parquet"
- config_name: "az-PY"
data_files:
- split: train
path: "data/az-PY/*.parquet"
- config_name: "az-RO"
data_files:
- split: train
path: "data/az-RO/*.parquet"
- config_name: "az-RU"
data_files:
- split: train
path: "data/az-RU/*.parquet"
- config_name: "az-SA"
data_files:
- split: train
path: "data/az-SA/*.parquet"
- config_name: "az-SE"
data_files:
- split: train
path: "data/az-SE/*.parquet"
- config_name: "az-SI"
data_files:
- split: train
path: "data/az-SI/*.parquet"
- config_name: "az-SK"
data_files:
- split: train
path: "data/az-SK/*.parquet"
- config_name: "az-TN"
data_files:
- split: train
path: "data/az-TN/*.parquet"
- config_name: "az-TO"
data_files:
- split: train
path: "data/az-TO/*.parquet"
- config_name: "az-TR"
data_files:
- split: train
path: "data/az-TR/*.parquet"
- config_name: "az-TV"
data_files:
- split: train
path: "data/az-TV/*.parquet"
- config_name: "az-UA"
data_files:
- split: train
path: "data/az-UA/*.parquet"
- config_name: "az-US"
data_files:
- split: train
path: "data/az-US/*.parquet"
- config_name: "az-UY"
data_files:
- split: train
path: "data/az-UY/*.parquet"
- config_name: "az-VN"
data_files:
- split: train
path: "data/az-VN/*.parquet"
- config_name: "az-WS"
data_files:
- split: train
path: "data/az-WS/*.parquet"
- config_name: "az-XX"
data_files:
- split: train
path: "data/az-XX/*.parquet"
- config_name: "azb-AZ"
data_files:
- split: train
path: "data/azb-AZ/*.parquet"
- config_name: "azb-IR"
data_files:
- split: train
path: "data/azb-IR/*.parquet"
- config_name: "azb-TR"
data_files:
- split: train
path: "data/azb-TR/*.parquet"
- config_name: "azb-US"
data_files:
- split: train
path: "data/azb-US/*.parquet"
- config_name: "azb-XX"
data_files:
- split: train
path: "data/azb-XX/*.parquet"
- config_name: "ba-BA"
data_files:
- split: train
path: "data/ba-BA/*.parquet"
- config_name: "ba-EU"
data_files:
- split: train
path: "data/ba-EU/*.parquet"
- config_name: "ba-RU"
data_files:
- split: train
path: "data/ba-RU/*.parquet"
- config_name: "ba-TV"
data_files:
- split: train
path: "data/ba-TV/*.parquet"
- config_name: "ba-XX"
data_files:
- split: train
path: "data/ba-XX/*.parquet"
- config_name: "be-BE"
data_files:
- split: train
path: "data/be-BE/*.parquet"
- config_name: "be-BY"
data_files:
- split: train
path: "data/be-BY/*.parquet"
- config_name: "be-CC"
data_files:
- split: train
path: "data/be-CC/*.parquet"
- config_name: "be-CN"
data_files:
- split: train
path: "data/be-CN/*.parquet"
- config_name: "be-CO"
data_files:
- split: train
path: "data/be-CO/*.parquet"
- config_name: "be-DE"
data_files:
- split: train
path: "data/be-DE/*.parquet"
- config_name: "be-EU"
data_files:
- split: train
path: "data/be-EU/*.parquet"
- config_name: "be-FM"
data_files:
- split: train
path: "data/be-FM/*.parquet"
- config_name: "be-FR"
data_files:
- split: train
path: "data/be-FR/*.parquet"
- config_name: "be-GB"
data_files:
- split: train
path: "data/be-GB/*.parquet"
- config_name: "be-GG"
data_files:
- split: train
path: "data/be-GG/*.parquet"
- config_name: "be-IO"
data_files:
- split: train
path: "data/be-IO/*.parquet"
- config_name: "be-IT"
data_files:
- split: train
path: "data/be-IT/*.parquet"
- config_name: "be-JP"
data_files:
- split: train
path: "data/be-JP/*.parquet"
- config_name: "be-KZ"
data_files:
- split: train
path: "data/be-KZ/*.parquet"
- config_name: "be-LT"
data_files:
- split: train
path: "data/be-LT/*.parquet"
- config_name: "be-ME"
data_files:
- split: train
path: "data/be-ME/*.parquet"
- config_name: "be-MN"
data_files:
- split: train
path: "data/be-MN/*.parquet"
- config_name: "be-PL"
data_files:
- split: train
path: "data/be-PL/*.parquet"
- config_name: "be-RU"
data_files:
- split: train
path: "data/be-RU/*.parquet"
- config_name: "be-UA"
data_files:
- split: train
path: "data/be-UA/*.parquet"
- config_name: "be-US"
data_files:
- split: train
path: "data/be-US/*.parquet"
- config_name: "be-VA"
data_files:
- split: train
path: "data/be-VA/*.parquet"
- config_name: "be-WS"
data_files:
- split: train
path: "data/be-WS/*.parquet"
- config_name: "be-XX"
data_files:
- split: train
path: "data/be-XX/*.parquet"
- config_name: "bg-AE"
data_files:
- split: train
path: "data/bg-AE/*.parquet"
- config_name: "bg-AM"
data_files:
- split: train
path: "data/bg-AM/*.parquet"
- config_name: "bg-AT"
data_files:
- split: train
path: "data/bg-AT/*.parquet"
- config_name: "bg-AU"
data_files:
- split: train
path: "data/bg-AU/*.parquet"
- config_name: "bg-BA"
data_files:
- split: train
path: "data/bg-BA/*.parquet"
- config_name: "bg-BE"
data_files:
- split: train
path: "data/bg-BE/*.parquet"
- config_name: "bg-BG"
data_files:
- split: train
path: "data/bg-BG/*.parquet"
- config_name: "bg-BQ"
data_files:
- split: train
path: "data/bg-BQ/*.parquet"
- config_name: "bg-BR"
data_files:
- split: train
path: "data/bg-BR/*.parquet"
- config_name: "bg-BU"
data_files:
- split: train
path: "data/bg-BU/*.parquet"
- config_name: "bg-BZ"
data_files:
- split: train
path: "data/bg-BZ/*.parquet"
- config_name: "bg-CC"
data_files:
- split: train
path: "data/bg-CC/*.parquet"
- config_name: "bg-CN"
data_files:
- split: train
path: "data/bg-CN/*.parquet"
- config_name: "bg-CO"
data_files:
- split: train
path: "data/bg-CO/*.parquet"
- config_name: "bg-CZ"
data_files:
- split: train
path: "data/bg-CZ/*.parquet"
- config_name: "bg-DE"
data_files:
- split: train
path: "data/bg-DE/*.parquet"
- config_name: "bg-DK"
data_files:
- split: train
path: "data/bg-DK/*.parquet"
- config_name: "bg-DO"
data_files:
- split: train
path: "data/bg-DO/*.parquet"
- config_name: "bg-EN"
data_files:
- split: train
path: "data/bg-EN/*.parquet"
- config_name: "bg-ES"
data_files:
- split: train
path: "data/bg-ES/*.parquet"
- config_name: "bg-EU"
data_files:
- split: train
path: "data/bg-EU/*.parquet"
- config_name: "bg-FM"
data_files:
- split: train
path: "data/bg-FM/*.parquet"
- config_name: "bg-FR"
data_files:
- split: train
path: "data/bg-FR/*.parquet"
- config_name: "bg-GB"
data_files:
- split: train
path: "data/bg-GB/*.parquet"
- config_name: "bg-GR"
data_files:
- split: train
path: "data/bg-GR/*.parquet"
- config_name: "bg-HU"
data_files:
- split: train
path: "data/bg-HU/*.parquet"
- config_name: "bg-IN"
data_files:
- split: train
path: "data/bg-IN/*.parquet"
- config_name: "bg-IO"
data_files:
- split: train
path: "data/bg-IO/*.parquet"
- config_name: "bg-IT"
data_files:
- split: train
path: "data/bg-IT/*.parquet"
- config_name: "bg-JP"
data_files:
- split: train
path: "data/bg-JP/*.parquet"
- config_name: "bg-LI"
data_files:
- split: train
path: "data/bg-LI/*.parquet"
- config_name: "bg-ME"
data_files:
- split: train
path: "data/bg-ME/*.parquet"
- config_name: "bg-MK"
data_files:
- split: train
path: "data/bg-MK/*.parquet"
- config_name: "bg-ML"
data_files:
- split: train
path: "data/bg-ML/*.parquet"
- config_name: "bg-NL"
data_files:
- split: train
path: "data/bg-NL/*.parquet"
- config_name: "bg-NZ"
data_files:
- split: train
path: "data/bg-NZ/*.parquet"
- config_name: "bg-PL"
data_files:
- split: train
path: "data/bg-PL/*.parquet"
- config_name: "bg-PT"
data_files:
- split: train
path: "data/bg-PT/*.parquet"
- config_name: "bg-PW"
data_files:
- split: train
path: "data/bg-PW/*.parquet"
- config_name: "bg-RO"
data_files:
- split: train
path: "data/bg-RO/*.parquet"
- config_name: "bg-RS"
data_files:
- split: train
path: "data/bg-RS/*.parquet"
- config_name: "bg-RU"
data_files:
- split: train
path: "data/bg-RU/*.parquet"
- config_name: "bg-SE"
data_files:
- split: train
path: "data/bg-SE/*.parquet"
- config_name: "bg-SI"
data_files:
- split: train
path: "data/bg-SI/*.parquet"
- config_name: "bg-SK"
data_files:
- split: train
path: "data/bg-SK/*.parquet"
- config_name: "bg-TK"
data_files:
- split: train
path: "data/bg-TK/*.parquet"
- config_name: "bg-TO"
data_files:
- split: train
path: "data/bg-TO/*.parquet"
- config_name: "bg-TR"
data_files:
- split: train
path: "data/bg-TR/*.parquet"
- config_name: "bg-TV"
data_files:
- split: train
path: "data/bg-TV/*.parquet"
- config_name: "bg-UA"
data_files:
- split: train
path: "data/bg-UA/*.parquet"
- config_name: "bg-US"
data_files:
- split: train
path: "data/bg-US/*.parquet"
- config_name: "bg-VA"
data_files:
- split: train
path: "data/bg-VA/*.parquet"
- config_name: "bg-WS"
data_files:
- split: train
path: "data/bg-WS/*.parquet"
- config_name: "bg-XX"
data_files:
- split: train
path: "data/bg-XX/*.parquet"
- config_name: "bn-BD"
data_files:
- split: train
path: "data/bn-BD/*.parquet"
- config_name: "bn-BR"
data_files:
- split: train
path: "data/bn-BR/*.parquet"
- config_name: "bn-CN"
data_files:
- split: train
path: "data/bn-CN/*.parquet"
- config_name: "bn-CO"
data_files:
- split: train
path: "data/bn-CO/*.parquet"
- config_name: "bn-DE"
data_files:
- split: train
path: "data/bn-DE/*.parquet"
- config_name: "bn-EU"
data_files:
- split: train
path: "data/bn-EU/*.parquet"
- config_name: "bn-GB"
data_files:
- split: train
path: "data/bn-GB/*.parquet"
- config_name: "bn-IN"
data_files:
- split: train
path: "data/bn-IN/*.parquet"
- config_name: "bn-TW"
data_files:
- split: train
path: "data/bn-TW/*.parquet"
- config_name: "bn-US"
data_files:
- split: train
path: "data/bn-US/*.parquet"
- config_name: "bn-XX"
data_files:
- split: train
path: "data/bn-XX/*.parquet"
- config_name: "bo-BT"
data_files:
- split: train
path: "data/bo-BT/*.parquet"
- config_name: "bo-GB"
data_files:
- split: train
path: "data/bo-GB/*.parquet"
- config_name: "bo-US"
data_files:
- split: train
path: "data/bo-US/*.parquet"
- config_name: "bo-XX"
data_files:
- split: train
path: "data/bo-XX/*.parquet"
- config_name: "br-BR"
data_files:
- split: train
path: "data/br-BR/*.parquet"
- config_name: "br-BZ"
data_files:
- split: train
path: "data/br-BZ/*.parquet"
- config_name: "br-FR"
data_files:
- split: train
path: "data/br-FR/*.parquet"
- config_name: "br-GB"
data_files:
- split: train
path: "data/br-GB/*.parquet"
- config_name: "br-XX"
data_files:
- split: train
path: "data/br-XX/*.parquet"
- config_name: "bs-IT"
data_files:
- split: train
path: "data/bs-IT/*.parquet"
- config_name: "ca-AD"
data_files:
- split: train
path: "data/ca-AD/*.parquet"
- config_name: "ca-AE"
data_files:
- split: train
path: "data/ca-AE/*.parquet"
- config_name: "ca-AR"
data_files:
- split: train
path: "data/ca-AR/*.parquet"
- config_name: "ca-AU"
data_files:
- split: train
path: "data/ca-AU/*.parquet"
- config_name: "ca-CA"
data_files:
- split: train
path: "data/ca-CA/*.parquet"
- config_name: "ca-CC"
data_files:
- split: train
path: "data/ca-CC/*.parquet"
- config_name: "ca-CH"
data_files:
- split: train
path: "data/ca-CH/*.parquet"
- config_name: "ca-CN"
data_files:
- split: train
path: "data/ca-CN/*.parquet"
- config_name: "ca-CO"
data_files:
- split: train
path: "data/ca-CO/*.parquet"
- config_name: "ca-CR"
data_files:
- split: train
path: "data/ca-CR/*.parquet"
- config_name: "ca-CZ"
data_files:
- split: train
path: "data/ca-CZ/*.parquet"
- config_name: "ca-DE"
data_files:
- split: train
path: "data/ca-DE/*.parquet"
- config_name: "ca-EN"
data_files:
- split: train
path: "data/ca-EN/*.parquet"
- config_name: "ca-ES"
data_files:
- split: train
path: "data/ca-ES/*.parquet"
- config_name: "ca-EU"
data_files:
- split: train
path: "data/ca-EU/*.parquet"
- config_name: "ca-FM"
data_files:
- split: train
path: "data/ca-FM/*.parquet"
- config_name: "ca-FR"
data_files:
- split: train
path: "data/ca-FR/*.parquet"
- config_name: "ca-GB"
data_files:
- split: train
path: "data/ca-GB/*.parquet"
- config_name: "ca-IO"
data_files:
- split: train
path: "data/ca-IO/*.parquet"
- config_name: "ca-IT"
data_files:
- split: train
path: "data/ca-IT/*.parquet"
- config_name: "ca-JP"
data_files:
- split: train
path: "data/ca-JP/*.parquet"
- config_name: "ca-KR"
data_files:
- split: train
path: "data/ca-KR/*.parquet"
- config_name: "ca-LA"
data_files:
- split: train
path: "data/ca-LA/*.parquet"
- config_name: "ca-LY"
data_files:
- split: train
path: "data/ca-LY/*.parquet"
- config_name: "ca-ME"
data_files:
- split: train
path: "data/ca-ME/*.parquet"
- config_name: "ca-MV"
data_files:
- split: train
path: "data/ca-MV/*.parquet"
- config_name: "ca-PT"
data_files:
- split: train
path: "data/ca-PT/*.parquet"
- config_name: "ca-RU"
data_files:
- split: train
path: "data/ca-RU/*.parquet"
- config_name: "ca-SE"
data_files:
- split: train
path: "data/ca-SE/*.parquet"
- config_name: "ca-SP"
data_files:
- split: train
path: "data/ca-SP/*.parquet"
- config_name: "ca-TV"
data_files:
- split: train
path: "data/ca-TV/*.parquet"
- config_name: "ca-US"
data_files:
- split: train
path: "data/ca-US/*.parquet"
- config_name: "ca-VA"
data_files:
- split: train
path: "data/ca-VA/*.parquet"
- config_name: "ca-VL"
data_files:
- split: train
path: "data/ca-VL/*.parquet"
- config_name: "ca-WS"
data_files:
- split: train
path: "data/ca-WS/*.parquet"
- config_name: "ca-XX"
data_files:
- split: train
path: "data/ca-XX/*.parquet"
- config_name: "ce-RU"
data_files:
- split: train
path: "data/ce-RU/*.parquet"
- config_name: "ce-XX"
data_files:
- split: train
path: "data/ce-XX/*.parquet"
- config_name: "ceb-GB"
data_files:
- split: train
path: "data/ceb-GB/*.parquet"
- config_name: "ceb-ID"
data_files:
- split: train
path: "data/ceb-ID/*.parquet"
- config_name: "ceb-IS"
data_files:
- split: train
path: "data/ceb-IS/*.parquet"
- config_name: "ceb-PH"
data_files:
- split: train
path: "data/ceb-PH/*.parquet"
- config_name: "ceb-US"
data_files:
- split: train
path: "data/ceb-US/*.parquet"
- config_name: "ceb-XX"
data_files:
- split: train
path: "data/ceb-XX/*.parquet"
- config_name: "ckb-AA"
data_files:
- split: train
path: "data/ckb-AA/*.parquet"
- config_name: "ckb-CO"
data_files:
- split: train
path: "data/ckb-CO/*.parquet"
- config_name: "ckb-DE"
data_files:
- split: train
path: "data/ckb-DE/*.parquet"
- config_name: "ckb-DK"
data_files:
- split: train
path: "data/ckb-DK/*.parquet"
- config_name: "ckb-GB"
data_files:
- split: train
path: "data/ckb-GB/*.parquet"
- config_name: "ckb-GP"
data_files:
- split: train
path: "data/ckb-GP/*.parquet"
- config_name: "ckb-IO"
data_files:
- split: train
path: "data/ckb-IO/*.parquet"
- config_name: "ckb-IQ"
data_files:
- split: train
path: "data/ckb-IQ/*.parquet"
- config_name: "ckb-IR"
data_files:
- split: train
path: "data/ckb-IR/*.parquet"
- config_name: "ckb-SE"
data_files:
- split: train
path: "data/ckb-SE/*.parquet"
- config_name: "ckb-SH"
data_files:
- split: train
path: "data/ckb-SH/*.parquet"
- config_name: "ckb-SK"
data_files:
- split: train
path: "data/ckb-SK/*.parquet"
- config_name: "ckb-SO"
data_files:
- split: train
path: "data/ckb-SO/*.parquet"
- config_name: "ckb-TR"
data_files:
- split: train
path: "data/ckb-TR/*.parquet"
- config_name: "ckb-TV"
data_files:
- split: train
path: "data/ckb-TV/*.parquet"
- config_name: "ckb-US"
data_files:
- split: train
path: "data/ckb-US/*.parquet"
- config_name: "ckb-XX"
data_files:
- split: train
path: "data/ckb-XX/*.parquet"
- config_name: "cs-AE"
data_files:
- split: train
path: "data/cs-AE/*.parquet"
- config_name: "cs-AG"
data_files:
- split: train
path: "data/cs-AG/*.parquet"
- config_name: "cs-AI"
data_files:
- split: train
path: "data/cs-AI/*.parquet"
- config_name: "cs-AM"
data_files:
- split: train
path: "data/cs-AM/*.parquet"
- config_name: "cs-AR"
data_files:
- split: train
path: "data/cs-AR/*.parquet"
- config_name: "cs-AS"
data_files:
- split: train
path: "data/cs-AS/*.parquet"
- config_name: "cs-AT"
data_files:
- split: train
path: "data/cs-AT/*.parquet"
- config_name: "cs-AU"
data_files:
- split: train
path: "data/cs-AU/*.parquet"
- config_name: "cs-AZ"
data_files:
- split: train
path: "data/cs-AZ/*.parquet"
- config_name: "cs-BE"
data_files:
- split: train
path: "data/cs-BE/*.parquet"
- config_name: "cs-BG"
data_files:
- split: train
path: "data/cs-BG/*.parquet"
- config_name: "cs-BR"
data_files:
- split: train
path: "data/cs-BR/*.parquet"
- config_name: "cs-BZ"
data_files:
- split: train
path: "data/cs-BZ/*.parquet"
- config_name: "cs-CA"
data_files:
- split: train
path: "data/cs-CA/*.parquet"
- config_name: "cs-CC"
data_files:
- split: train
path: "data/cs-CC/*.parquet"
- config_name: "cs-CD"
data_files:
- split: train
path: "data/cs-CD/*.parquet"
- config_name: "cs-CH"
data_files:
- split: train
path: "data/cs-CH/*.parquet"
- config_name: "cs-CL"
data_files:
- split: train
path: "data/cs-CL/*.parquet"
- config_name: "cs-CN"
data_files:
- split: train
path: "data/cs-CN/*.parquet"
- config_name: "cs-CO"
data_files:
- split: train
path: "data/cs-CO/*.parquet"
- config_name: "cs-CS"
data_files:
- split: train
path: "data/cs-CS/*.parquet"
- config_name: "cs-CX"
data_files:
- split: train
path: "data/cs-CX/*.parquet"
- config_name: "cs-CY"
data_files:
- split: train
path: "data/cs-CY/*.parquet"
- config_name: "cs-CZ"
data_files:
- split: train
path: "data/cs-CZ/*.parquet"
- config_name: "cs-DE"
data_files:
- split: train
path: "data/cs-DE/*.parquet"
- config_name: "cs-DK"
data_files:
- split: train
path: "data/cs-DK/*.parquet"
- config_name: "cs-DO"
data_files:
- split: train
path: "data/cs-DO/*.parquet"
- config_name: "cs-EE"
data_files:
- split: train
path: "data/cs-EE/*.parquet"
- config_name: "cs-EN"
data_files:
- split: train
path: "data/cs-EN/*.parquet"
- config_name: "cs-ES"
data_files:
- split: train
path: "data/cs-ES/*.parquet"
- config_name: "cs-EU"
data_files:
- split: train
path: "data/cs-EU/*.parquet"
- config_name: "cs-FI"
data_files:
- split: train
path: "data/cs-FI/*.parquet"
- config_name: "cs-FM"
data_files:
- split: train
path: "data/cs-FM/*.parquet"
- config_name: "cs-FR"
data_files:
- split: train
path: "data/cs-FR/*.parquet"
- config_name: "cs-GB"
data_files:
- split: train
path: "data/cs-GB/*.parquet"
- config_name: "cs-GG"
data_files:
- split: train
path: "data/cs-GG/*.parquet"
- config_name: "cs-GL"
data_files:
- split: train
path: "data/cs-GL/*.parquet"
- config_name: "cs-GQ"
data_files:
- split: train
path: "data/cs-GQ/*.parquet"
- config_name: "cs-GR"
data_files:
- split: train
path: "data/cs-GR/*.parquet"
- config_name: "cs-HK"
data_files:
- split: train
path: "data/cs-HK/*.parquet"
- config_name: "cs-HR"
data_files:
- split: train
path: "data/cs-HR/*.parquet"
- config_name: "cs-HU"
data_files:
- split: train
path: "data/cs-HU/*.parquet"
- config_name: "cs-ID"
data_files:
- split: train
path: "data/cs-ID/*.parquet"
- config_name: "cs-IE"
data_files:
- split: train
path: "data/cs-IE/*.parquet"
- config_name: "cs-IL"
data_files:
- split: train
path: "data/cs-IL/*.parquet"
- config_name: "cs-IN"
data_files:
- split: train
path: "data/cs-IN/*.parquet"
- config_name: "cs-IO"
data_files:
- split: train
path: "data/cs-IO/*.parquet"
- config_name: "cs-IR"
data_files:
- split: train
path: "data/cs-IR/*.parquet"
- config_name: "cs-IS"
data_files:
- split: train
path: "data/cs-IS/*.parquet"
- config_name: "cs-IT"
data_files:
- split: train
path: "data/cs-IT/*.parquet"
- config_name: "cs-JP"
data_files:
- split: train
path: "data/cs-JP/*.parquet"
- config_name: "cs-KE"
data_files:
- split: train
path: "data/cs-KE/*.parquet"
- config_name: "cs-KR"
data_files:
- split: train
path: "data/cs-KR/*.parquet"
- config_name: "cs-LA"
data_files:
- split: train
path: "data/cs-LA/*.parquet"
- config_name: "cs-LT"
data_files:
- split: train
path: "data/cs-LT/*.parquet"
- config_name: "cs-LU"
data_files:
- split: train
path: "data/cs-LU/*.parquet"
- config_name: "cs-LY"
data_files:
- split: train
path: "data/cs-LY/*.parquet"
- config_name: "cs-ME"
data_files:
- split: train
path: "data/cs-ME/*.parquet"
- config_name: "cs-ML"
data_files:
- split: train
path: "data/cs-ML/*.parquet"
- config_name: "cs-MX"
data_files:
- split: train
path: "data/cs-MX/*.parquet"
- config_name: "cs-NL"
data_files:
- split: train
path: "data/cs-NL/*.parquet"
- config_name: "cs-PH"
data_files:
- split: train
path: "data/cs-PH/*.parquet"
- config_name: "cs-PL"
data_files:
- split: train
path: "data/cs-PL/*.parquet"
- config_name: "cs-PR"
data_files:
- split: train
path: "data/cs-PR/*.parquet"
- config_name: "cs-PT"
data_files:
- split: train
path: "data/cs-PT/*.parquet"
- config_name: "cs-PW"
data_files:
- split: train
path: "data/cs-PW/*.parquet"
- config_name: "cs-RE"
data_files:
- split: train
path: "data/cs-RE/*.parquet"
- config_name: "cs-RO"
data_files:
- split: train
path: "data/cs-RO/*.parquet"
- config_name: "cs-RS"
data_files:
- split: train
path: "data/cs-RS/*.parquet"
- config_name: "cs-RU"
data_files:
- split: train
path: "data/cs-RU/*.parquet"
- config_name: "cs-SE"
data_files:
- split: train
path: "data/cs-SE/*.parquet"
- config_name: "cs-SG"
data_files:
- split: train
path: "data/cs-SG/*.parquet"
- config_name: "cs-SI"
data_files:
- split: train
path: "data/cs-SI/*.parquet"
- config_name: "cs-SK"
data_files:
- split: train
path: "data/cs-SK/*.parquet"
- config_name: "cs-TK"
data_files:
- split: train
path: "data/cs-TK/*.parquet"
- config_name: "cs-TL"
data_files:
- split: train
path: "data/cs-TL/*.parquet"
- config_name: "cs-TO"
data_files:
- split: train
path: "data/cs-TO/*.parquet"
- config_name: "cs-TR"
data_files:
- split: train
path: "data/cs-TR/*.parquet"
- config_name: "cs-TV"
data_files:
- split: train
path: "data/cs-TV/*.parquet"
- config_name: "cs-TW"
data_files:
- split: train
path: "data/cs-TW/*.parquet"
- config_name: "cs-UA"
data_files:
- split: train
path: "data/cs-UA/*.parquet"
- config_name: "cs-US"
data_files:
- split: train
path: "data/cs-US/*.parquet"
- config_name: "cs-VA"
data_files:
- split: train
path: "data/cs-VA/*.parquet"
- config_name: "cs-VN"
data_files:
- split: train
path: "data/cs-VN/*.parquet"
- config_name: "cs-WS"
data_files:
- split: train
path: "data/cs-WS/*.parquet"
- config_name: "cs-XK"
data_files:
- split: train
path: "data/cs-XK/*.parquet"
- config_name: "cs-XX"
data_files:
- split: train
path: "data/cs-XX/*.parquet"
- config_name: "cs-ZA"
data_files:
- split: train
path: "data/cs-ZA/*.parquet"
- config_name: "cv-EO"
data_files:
- split: train
path: "data/cv-EO/*.parquet"
- config_name: "cv-RU"
data_files:
- split: train
path: "data/cv-RU/*.parquet"
- config_name: "cv-XX"
data_files:
- split: train
path: "data/cv-XX/*.parquet"
- config_name: "cy-AI"
data_files:
- split: train
path: "data/cy-AI/*.parquet"
- config_name: "cy-CC"
data_files:
- split: train
path: "data/cy-CC/*.parquet"
- config_name: "cy-CO"
data_files:
- split: train
path: "data/cy-CO/*.parquet"
- config_name: "cy-CY"
data_files:
- split: train
path: "data/cy-CY/*.parquet"
- config_name: "cy-DE"
data_files:
- split: train
path: "data/cy-DE/*.parquet"
- config_name: "cy-ES"
data_files:
- split: train
path: "data/cy-ES/*.parquet"
- config_name: "cy-EU"
data_files:
- split: train
path: "data/cy-EU/*.parquet"
- config_name: "cy-FM"
data_files:
- split: train
path: "data/cy-FM/*.parquet"
- config_name: "cy-GB"
data_files:
- split: train
path: "data/cy-GB/*.parquet"
- config_name: "cy-IE"
data_files:
- split: train
path: "data/cy-IE/*.parquet"
- config_name: "cy-IO"
data_files:
- split: train
path: "data/cy-IO/*.parquet"
- config_name: "cy-JP"
data_files:
- split: train
path: "data/cy-JP/*.parquet"
- config_name: "cy-TV"
data_files:
- split: train
path: "data/cy-TV/*.parquet"
- config_name: "cy-TW"
data_files:
- split: train
path: "data/cy-TW/*.parquet"
- config_name: "cy-US"
data_files:
- split: train
path: "data/cy-US/*.parquet"
- config_name: "cy-XX"
data_files:
- split: train
path: "data/cy-XX/*.parquet"
- config_name: "da-AF"
data_files:
- split: train
path: "data/da-AF/*.parquet"
- config_name: "da-AG"
data_files:
- split: train
path: "data/da-AG/*.parquet"
- config_name: "da-AI"
data_files:
- split: train
path: "data/da-AI/*.parquet"
- config_name: "da-AS"
data_files:
- split: train
path: "data/da-AS/*.parquet"
- config_name: "da-AT"
data_files:
- split: train
path: "data/da-AT/*.parquet"
- config_name: "da-AU"
data_files:
- split: train
path: "data/da-AU/*.parquet"
- config_name: "da-BE"
data_files:
- split: train
path: "data/da-BE/*.parquet"
- config_name: "da-BG"
data_files:
- split: train
path: "data/da-BG/*.parquet"
- config_name: "da-BR"
data_files:
- split: train
path: "data/da-BR/*.parquet"
- config_name: "da-BZ"
data_files:
- split: train
path: "data/da-BZ/*.parquet"
- config_name: "da-CA"
data_files:
- split: train
path: "data/da-CA/*.parquet"
- config_name: "da-CC"
data_files:
- split: train
path: "data/da-CC/*.parquet"
- config_name: "da-CH"
data_files:
- split: train
path: "data/da-CH/*.parquet"
- config_name: "da-CL"
data_files:
- split: train
path: "data/da-CL/*.parquet"
- config_name: "da-CN"
data_files:
- split: train
path: "data/da-CN/*.parquet"
- config_name: "da-CO"
data_files:
- split: train
path: "data/da-CO/*.parquet"
- config_name: "da-CZ"
data_files:
- split: train
path: "data/da-CZ/*.parquet"
- config_name: "da-DA"
data_files:
- split: train
path: "data/da-DA/*.parquet"
- config_name: "da-DE"
data_files:
- split: train
path: "data/da-DE/*.parquet"
- config_name: "da-DK"
data_files:
- split: train
path: "data/da-DK/*.parquet"
- config_name: "da-EE"
data_files:
- split: train
path: "data/da-EE/*.parquet"
- config_name: "da-EN"
data_files:
- split: train
path: "data/da-EN/*.parquet"
- config_name: "da-ES"
data_files:
- split: train
path: "data/da-ES/*.parquet"
- config_name: "da-EU"
data_files:
- split: train
path: "data/da-EU/*.parquet"
- config_name: "da-FI"
data_files:
- split: train
path: "data/da-FI/*.parquet"
- config_name: "da-FM"
data_files:
- split: train
path: "data/da-FM/*.parquet"
- config_name: "da-FO"
data_files:
- split: train
path: "data/da-FO/*.parquet"
- config_name: "da-FR"
data_files:
- split: train
path: "data/da-FR/*.parquet"
- config_name: "da-GB"
data_files:
- split: train
path: "data/da-GB/*.parquet"
- config_name: "da-GG"
data_files:
- split: train
path: "data/da-GG/*.parquet"
- config_name: "da-GL"
data_files:
- split: train
path: "data/da-GL/*.parquet"
- config_name: "da-GR"
data_files:
- split: train
path: "data/da-GR/*.parquet"
- config_name: "da-HU"
data_files:
- split: train
path: "data/da-HU/*.parquet"
- config_name: "da-IE"
data_files:
- split: train
path: "data/da-IE/*.parquet"
- config_name: "da-IL"
data_files:
- split: train
path: "data/da-IL/*.parquet"
- config_name: "da-IN"
data_files:
- split: train
path: "data/da-IN/*.parquet"
- config_name: "da-IO"
data_files:
- split: train
path: "data/da-IO/*.parquet"
- config_name: "da-IS"
data_files:
- split: train
path: "data/da-IS/*.parquet"
- config_name: "da-IT"
data_files:
- split: train
path: "data/da-IT/*.parquet"
- config_name: "da-KZ"
data_files:
- split: train
path: "data/da-KZ/*.parquet"
- config_name: "da-LU"
data_files:
- split: train
path: "data/da-LU/*.parquet"
- config_name: "da-ME"
data_files:
- split: train
path: "data/da-ME/*.parquet"
- config_name: "da-MX"
data_files:
- split: train
path: "data/da-MX/*.parquet"
- config_name: "da-NB"
data_files:
- split: train
path: "data/da-NB/*.parquet"
- config_name: "da-NE"
data_files:
- split: train
path: "data/da-NE/*.parquet"
- config_name: "da-NL"
data_files:
- split: train
path: "data/da-NL/*.parquet"
- config_name: "da-NO"
data_files:
- split: train
path: "data/da-NO/*.parquet"
- config_name: "da-NU"
data_files:
- split: train
path: "data/da-NU/*.parquet"
- config_name: "da-PE"
data_files:
- split: train
path: "data/da-PE/*.parquet"
- config_name: "da-PL"
data_files:
- split: train
path: "data/da-PL/*.parquet"
- config_name: "da-PS"
data_files:
- split: train
path: "data/da-PS/*.parquet"
- config_name: "da-PT"
data_files:
- split: train
path: "data/da-PT/*.parquet"
- config_name: "da-PW"
data_files:
- split: train
path: "data/da-PW/*.parquet"
- config_name: "da-RO"
data_files:
- split: train
path: "data/da-RO/*.parquet"
- config_name: "da-RU"
data_files:
- split: train
path: "data/da-RU/*.parquet"
- config_name: "da-SE"
data_files:
- split: train
path: "data/da-SE/*.parquet"
- config_name: "da-SI"
data_files:
- split: train
path: "data/da-SI/*.parquet"
- config_name: "da-SK"
data_files:
- split: train
path: "data/da-SK/*.parquet"
- config_name: "da-SV"
data_files:
- split: train
path: "data/da-SV/*.parquet"
- config_name: "da-SZ"
data_files:
- split: train
path: "data/da-SZ/*.parquet"
- config_name: "da-TH"
data_files:
- split: train
path: "data/da-TH/*.parquet"
- config_name: "da-TR"
data_files:
- split: train
path: "data/da-TR/*.parquet"
- config_name: "da-TV"
data_files:
- split: train
path: "data/da-TV/*.parquet"
- config_name: "da-UA"
data_files:
- split: train
path: "data/da-UA/*.parquet"
- config_name: "da-US"
data_files:
- split: train
path: "data/da-US/*.parquet"
- config_name: "da-WS"
data_files:
- split: train
path: "data/da-WS/*.parquet"
- config_name: "da-XX"
data_files:
- split: train
path: "data/da-XX/*.parquet"
- config_name: "da-ZA"
data_files:
- split: train
path: "data/da-ZA/*.parquet"
- config_name: "de-AA"
data_files:
- split: train
path: "data/de-AA/*.parquet"
- config_name: "de-AD"
data_files:
- split: train
path: "data/de-AD/*.parquet"
- config_name: "de-AE"
data_files:
- split: train
path: "data/de-AE/*.parquet"
- config_name: "de-AG"
data_files:
- split: train
path: "data/de-AG/*.parquet"
- config_name: "de-AI"
data_files:
- split: train
path: "data/de-AI/*.parquet"
- config_name: "de-AL"
data_files:
- split: train
path: "data/de-AL/*.parquet"
- config_name: "de-AM"
data_files:
- split: train
path: "data/de-AM/*.parquet"
- config_name: "de-AR"
data_files:
- split: train
path: "data/de-AR/*.parquet"
- config_name: "de-AS"
data_files:
- split: train
path: "data/de-AS/*.parquet"
- config_name: "de-AT"
data_files:
- split: train
path: "data/de-AT/*.parquet"
- config_name: "de-AU"
data_files:
- split: train
path: "data/de-AU/*.parquet"
- config_name: "de-AX"
data_files:
- split: train
path: "data/de-AX/*.parquet"
- config_name: "de-AZ"
data_files:
- split: train
path: "data/de-AZ/*.parquet"
- config_name: "de-BA"
data_files:
- split: train
path: "data/de-BA/*.parquet"
- config_name: "de-BD"
data_files:
- split: train
path: "data/de-BD/*.parquet"
- config_name: "de-BE"
data_files:
- split: train
path: "data/de-BE/*.parquet"
- config_name: "de-BG"
data_files:
- split: train
path: "data/de-BG/*.parquet"
- config_name: "de-BM"
data_files:
- split: train
path: "data/de-BM/*.parquet"
- config_name: "de-BR"
data_files:
- split: train
path: "data/de-BR/*.parquet"
- config_name: "de-BS"
data_files:
- split: train
path: "data/de-BS/*.parquet"
- config_name: "de-BY"
data_files:
- split: train
path: "data/de-BY/*.parquet"
- config_name: "de-BZ"
data_files:
- split: train
path: "data/de-BZ/*.parquet"
- config_name: "de-CA"
data_files:
- split: train
path: "data/de-CA/*.parquet"
- config_name: "de-CC"
data_files:
- split: train
path: "data/de-CC/*.parquet"
- config_name: "de-CD"
data_files:
- split: train
path: "data/de-CD/*.parquet"
- config_name: "de-CF"
data_files:
- split: train
path: "data/de-CF/*.parquet"
- config_name: "de-CH"
data_files:
- split: train
path: "data/de-CH/*.parquet"
- config_name: "de-CL"
data_files:
- split: train
path: "data/de-CL/*.parquet"
- config_name: "de-CM"
data_files:
- split: train
path: "data/de-CM/*.parquet"
- config_name: "de-CN"
data_files:
- split: train
path: "data/de-CN/*.parquet"
- config_name: "de-CO"
data_files:
- split: train
path: "data/de-CO/*.parquet"
- config_name: "de-CR"
data_files:
- split: train
path: "data/de-CR/*.parquet"
- config_name: "de-CS"
data_files:
- split: train
path: "data/de-CS/*.parquet"
- config_name: "de-CU"
data_files:
- split: train
path: "data/de-CU/*.parquet"
- config_name: "de-CX"
data_files:
- split: train
path: "data/de-CX/*.parquet"
- config_name: "de-CY"
data_files:
- split: train
path: "data/de-CY/*.parquet"
- config_name: "de-CZ"
data_files:
- split: train
path: "data/de-CZ/*.parquet"
- config_name: "de-DE"
data_files:
- split: train
path: "data/de-DE/*.parquet"
- config_name: "de-DK"
data_files:
- split: train
path: "data/de-DK/*.parquet"
- config_name: "de-DO"
data_files:
- split: train
path: "data/de-DO/*.parquet"
- config_name: "de-DS"
data_files:
- split: train
path: "data/de-DS/*.parquet"
- config_name: "de-DU"
data_files:
- split: train
path: "data/de-DU/*.parquet"
- config_name: "de-EC"
data_files:
- split: train
path: "data/de-EC/*.parquet"
- config_name: "de-EE"
data_files:
- split: train
path: "data/de-EE/*.parquet"
- config_name: "de-EG"
data_files:
- split: train
path: "data/de-EG/*.parquet"
- config_name: "de-EN"
data_files:
- split: train
path: "data/de-EN/*.parquet"
- config_name: "de-ES"
data_files:
- split: train
path: "data/de-ES/*.parquet"
- config_name: "de-ET"
data_files:
- split: train
path: "data/de-ET/*.parquet"
- config_name: "de-EU"
data_files:
- split: train
path: "data/de-EU/*.parquet"
- config_name: "de-FI"
data_files:
- split: train
path: "data/de-FI/*.parquet"
- config_name: "de-FM"
data_files:
- split: train
path: "data/de-FM/*.parquet"
- config_name: "de-FR"
data_files:
- split: train
path: "data/de-FR/*.parquet"
- config_name: "de-FY"
data_files:
- split: train
path: "data/de-FY/*.parquet"
- config_name: "de-GA"
data_files:
- split: train
path: "data/de-GA/*.parquet"
- config_name: "de-GB"
data_files:
- split: train
path: "data/de-GB/*.parquet"
- config_name: "de-GE"
data_files:
- split: train
path: "data/de-GE/*.parquet"
- config_name: "de-GG"
data_files:
- split: train
path: "data/de-GG/*.parquet"
- config_name: "de-GL"
data_files:
- split: train
path: "data/de-GL/*.parquet"
- config_name: "de-GP"
data_files:
- split: train
path: "data/de-GP/*.parquet"
- config_name: "de-GQ"
data_files:
- split: train
path: "data/de-GQ/*.parquet"
- config_name: "de-GR"
data_files:
- split: train
path: "data/de-GR/*.parquet"
- config_name: "de-GT"
data_files:
- split: train
path: "data/de-GT/*.parquet"
- config_name: "de-GX"
data_files:
- split: train
path: "data/de-GX/*.parquet"
- config_name: "de-HK"
data_files:
- split: train
path: "data/de-HK/*.parquet"
- config_name: "de-HN"
data_files:
- split: train
path: "data/de-HN/*.parquet"
- config_name: "de-HR"
data_files:
- split: train
path: "data/de-HR/*.parquet"
- config_name: "de-HU"
data_files:
- split: train
path: "data/de-HU/*.parquet"
- config_name: "de-ID"
data_files:
- split: train
path: "data/de-ID/*.parquet"
- config_name: "de-IE"
data_files:
- split: train
path: "data/de-IE/*.parquet"
- config_name: "de-IL"
data_files:
- split: train
path: "data/de-IL/*.parquet"
- config_name: "de-IM"
data_files:
- split: train
path: "data/de-IM/*.parquet"
- config_name: "de-IN"
data_files:
- split: train
path: "data/de-IN/*.parquet"
- config_name: "de-IO"
data_files:
- split: train
path: "data/de-IO/*.parquet"
- config_name: "de-IQ"
data_files:
- split: train
path: "data/de-IQ/*.parquet"
- config_name: "de-IR"
data_files:
- split: train
path: "data/de-IR/*.parquet"
- config_name: "de-IS"
data_files:
- split: train
path: "data/de-IS/*.parquet"
- config_name: "de-IT"
data_files:
- split: train
path: "data/de-IT/*.parquet"
- config_name: "de-JP"
data_files:
- split: train
path: "data/de-JP/*.parquet"
- config_name: "de-KG"
data_files:
- split: train
path: "data/de-KG/*.parquet"
- config_name: "de-KR"
data_files:
- split: train
path: "data/de-KR/*.parquet"
- config_name: "de-KZ"
data_files:
- split: train
path: "data/de-KZ/*.parquet"
- config_name: "de-LA"
data_files:
- split: train
path: "data/de-LA/*.parquet"
- config_name: "de-LB"
data_files:
- split: train
path: "data/de-LB/*.parquet"
- config_name: "de-LC"
data_files:
- split: train
path: "data/de-LC/*.parquet"
- config_name: "de-LI"
data_files:
- split: train
path: "data/de-LI/*.parquet"
- config_name: "de-LK"
data_files:
- split: train
path: "data/de-LK/*.parquet"
- config_name: "de-LS"
data_files:
- split: train
path: "data/de-LS/*.parquet"
- config_name: "de-LT"
data_files:
- split: train
path: "data/de-LT/*.parquet"
- config_name: "de-LU"
data_files:
- split: train
path: "data/de-LU/*.parquet"
- config_name: "de-LV"
data_files:
- split: train
path: "data/de-LV/*.parquet"
- config_name: "de-LY"
data_files:
- split: train
path: "data/de-LY/*.parquet"
- config_name: "de-MA"
data_files:
- split: train
path: "data/de-MA/*.parquet"
- config_name: "de-MD"
data_files:
- split: train
path: "data/de-MD/*.parquet"
- config_name: "de-ME"
data_files:
- split: train
path: "data/de-ME/*.parquet"
- config_name: "de-MG"
data_files:
- split: train
path: "data/de-MG/*.parquet"
- config_name: "de-MK"
data_files:
- split: train
path: "data/de-MK/*.parquet"
- config_name: "de-ML"
data_files:
- split: train
path: "data/de-ML/*.parquet"
- config_name: "de-MN"
data_files:
- split: train
path: "data/de-MN/*.parquet"
- config_name: "de-MS"
data_files:
- split: train
path: "data/de-MS/*.parquet"
- config_name: "de-MT"
data_files:
- split: train
path: "data/de-MT/*.parquet"
- config_name: "de-MX"
data_files:
- split: train
path: "data/de-MX/*.parquet"
- config_name: "de-MY"
data_files:
- split: train
path: "data/de-MY/*.parquet"
- config_name: "de-NA"
data_files:
- split: train
path: "data/de-NA/*.parquet"
- config_name: "de-NF"
data_files:
- split: train
path: "data/de-NF/*.parquet"
- config_name: "de-NG"
data_files:
- split: train
path: "data/de-NG/*.parquet"
- config_name: "de-NL"
data_files:
- split: train
path: "data/de-NL/*.parquet"
- config_name: "de-NO"
data_files:
- split: train
path: "data/de-NO/*.parquet"
- config_name: "de-NP"
data_files:
- split: train
path: "data/de-NP/*.parquet"
- config_name: "de-NU"
data_files:
- split: train
path: "data/de-NU/*.parquet"
- config_name: "de-NZ"
data_files:
- split: train
path: "data/de-NZ/*.parquet"
- config_name: "de-OS"
data_files:
- split: train
path: "data/de-OS/*.parquet"
- config_name: "de-PA"
data_files:
- split: train
path: "data/de-PA/*.parquet"
- config_name: "de-PE"
data_files:
- split: train
path: "data/de-PE/*.parquet"
- config_name: "de-PH"
data_files:
- split: train
path: "data/de-PH/*.parquet"
- config_name: "de-PK"
data_files:
- split: train
path: "data/de-PK/*.parquet"
- config_name: "de-PL"
data_files:
- split: train
path: "data/de-PL/*.parquet"
- config_name: "de-PM"
data_files:
- split: train
path: "data/de-PM/*.parquet"
- config_name: "de-PN"
data_files:
- split: train
path: "data/de-PN/*.parquet"
- config_name: "de-PR"
data_files:
- split: train
path: "data/de-PR/*.parquet"
- config_name: "de-PT"
data_files:
- split: train
path: "data/de-PT/*.parquet"
- config_name: "de-PW"
data_files:
- split: train
path: "data/de-PW/*.parquet"
- config_name: "de-QA"
data_files:
- split: train
path: "data/de-QA/*.parquet"
- config_name: "de-RO"
data_files:
- split: train
path: "data/de-RO/*.parquet"
- config_name: "de-RS"
data_files:
- split: train
path: "data/de-RS/*.parquet"
- config_name: "de-RT"
data_files:
- split: train
path: "data/de-RT/*.parquet"
- config_name: "de-RU"
data_files:
- split: train
path: "data/de-RU/*.parquet"
- config_name: "de-SA"
data_files:
- split: train
path: "data/de-SA/*.parquet"
- config_name: "de-SB"
data_files:
- split: train
path: "data/de-SB/*.parquet"
- config_name: "de-SC"
data_files:
- split: train
path: "data/de-SC/*.parquet"
- config_name: "de-SE"
data_files:
- split: train
path: "data/de-SE/*.parquet"
- config_name: "de-SG"
data_files:
- split: train
path: "data/de-SG/*.parquet"
- config_name: "de-SH"
data_files:
- split: train
path: "data/de-SH/*.parquet"
- config_name: "de-SI"
data_files:
- split: train
path: "data/de-SI/*.parquet"
- config_name: "de-SK"
data_files:
- split: train
path: "data/de-SK/*.parquet"
- config_name: "de-SM"
data_files:
- split: train
path: "data/de-SM/*.parquet"
- config_name: "de-SO"
data_files:
- split: train
path: "data/de-SO/*.parquet"
- config_name: "de-ST"
data_files:
- split: train
path: "data/de-ST/*.parquet"
- config_name: "de-SV"
data_files:
- split: train
path: "data/de-SV/*.parquet"
- config_name: "de-SX"
data_files:
- split: train
path: "data/de-SX/*.parquet"
- config_name: "de-TB"
data_files:
- split: train
path: "data/de-TB/*.parquet"
- config_name: "de-TC"
data_files:
- split: train
path: "data/de-TC/*.parquet"
- config_name: "de-TG"
data_files:
- split: train
path: "data/de-TG/*.parquet"
- config_name: "de-TH"
data_files:
- split: train
path: "data/de-TH/*.parquet"
- config_name: "de-TJ"
data_files:
- split: train
path: "data/de-TJ/*.parquet"
- config_name: "de-TK"
data_files:
- split: train
path: "data/de-TK/*.parquet"
- config_name: "de-TL"
data_files:
- split: train
path: "data/de-TL/*.parquet"
- config_name: "de-TM"
data_files:
- split: train
path: "data/de-TM/*.parquet"
- config_name: "de-TO"
data_files:
- split: train
path: "data/de-TO/*.parquet"
- config_name: "de-TR"
data_files:
- split: train
path: "data/de-TR/*.parquet"
- config_name: "de-TV"
data_files:
- split: train
path: "data/de-TV/*.parquet"
- config_name: "de-TW"
data_files:
- split: train
path: "data/de-TW/*.parquet"
- config_name: "de-UA"
data_files:
- split: train
path: "data/de-UA/*.parquet"
- config_name: "de-UK"
data_files:
- split: train
path: "data/de-UK/*.parquet"
- config_name: "de-US"
data_files:
- split: train
path: "data/de-US/*.parquet"
- config_name: "de-UY"
data_files:
- split: train
path: "data/de-UY/*.parquet"
- config_name: "de-UZ"
data_files:
- split: train
path: "data/de-UZ/*.parquet"
- config_name: "de-VA"
data_files:
- split: train
path: "data/de-VA/*.parquet"
- config_name: "de-VC"
data_files:
- split: train
path: "data/de-VC/*.parquet"
- config_name: "de-VE"
data_files:
- split: train
path: "data/de-VE/*.parquet"
- config_name: "de-VN"
data_files:
- split: train
path: "data/de-VN/*.parquet"
- config_name: "de-VU"
data_files:
- split: train
path: "data/de-VU/*.parquet"
- config_name: "de-WS"
data_files:
- split: train
path: "data/de-WS/*.parquet"
- config_name: "de-XX"
data_files:
- split: train
path: "data/de-XX/*.parquet"
- config_name: "de-ZA"
data_files:
- split: train
path: "data/de-ZA/*.parquet"
- config_name: "de-ZW"
data_files:
- split: train
path: "data/de-ZW/*.parquet"
- config_name: "de-ZZ"
data_files:
- split: train
path: "data/de-ZZ/*.parquet"
- config_name: "el-AI"
data_files:
- split: train
path: "data/el-AI/*.parquet"
- config_name: "el-AL"
data_files:
- split: train
path: "data/el-AL/*.parquet"
- config_name: "el-AM"
data_files:
- split: train
path: "data/el-AM/*.parquet"
- config_name: "el-AR"
data_files:
- split: train
path: "data/el-AR/*.parquet"
- config_name: "el-AU"
data_files:
- split: train
path: "data/el-AU/*.parquet"
- config_name: "el-BE"
data_files:
- split: train
path: "data/el-BE/*.parquet"
- config_name: "el-BG"
data_files:
- split: train
path: "data/el-BG/*.parquet"
- config_name: "el-BM"
data_files:
- split: train
path: "data/el-BM/*.parquet"
- config_name: "el-BO"
data_files:
- split: train
path: "data/el-BO/*.parquet"
- config_name: "el-BR"
data_files:
- split: train
path: "data/el-BR/*.parquet"
- config_name: "el-BZ"
data_files:
- split: train
path: "data/el-BZ/*.parquet"
- config_name: "el-CA"
data_files:
- split: train
path: "data/el-CA/*.parquet"
- config_name: "el-CC"
data_files:
- split: train
path: "data/el-CC/*.parquet"
- config_name: "el-CF"
data_files:
- split: train
path: "data/el-CF/*.parquet"
- config_name: "el-CH"
data_files:
- split: train
path: "data/el-CH/*.parquet"
- config_name: "el-CN"
data_files:
- split: train
path: "data/el-CN/*.parquet"
- config_name: "el-CO"
data_files:
- split: train
path: "data/el-CO/*.parquet"
- config_name: "el-CY"
data_files:
- split: train
path: "data/el-CY/*.parquet"
- config_name: "el-CZ"
data_files:
- split: train
path: "data/el-CZ/*.parquet"
- config_name: "el-DE"
data_files:
- split: train
path: "data/el-DE/*.parquet"
- config_name: "el-DJ"
data_files:
- split: train
path: "data/el-DJ/*.parquet"
- config_name: "el-DK"
data_files:
- split: train
path: "data/el-DK/*.parquet"
- config_name: "el-EL"
data_files:
- split: train
path: "data/el-EL/*.parquet"
- config_name: "el-EN"
data_files:
- split: train
path: "data/el-EN/*.parquet"
- config_name: "el-ES"
data_files:
- split: train
path: "data/el-ES/*.parquet"
- config_name: "el-EU"
data_files:
- split: train
path: "data/el-EU/*.parquet"
- config_name: "el-FI"
data_files:
- split: train
path: "data/el-FI/*.parquet"
- config_name: "el-FM"
data_files:
- split: train
path: "data/el-FM/*.parquet"
- config_name: "el-FR"
data_files:
- split: train
path: "data/el-FR/*.parquet"
- config_name: "el-GA"
data_files:
- split: train
path: "data/el-GA/*.parquet"
- config_name: "el-GB"
data_files:
- split: train
path: "data/el-GB/*.parquet"
- config_name: "el-GQ"
data_files:
- split: train
path: "data/el-GQ/*.parquet"
- config_name: "el-GR"
data_files:
- split: train
path: "data/el-GR/*.parquet"
- config_name: "el-HR"
data_files:
- split: train
path: "data/el-HR/*.parquet"
- config_name: "el-IL"
data_files:
- split: train
path: "data/el-IL/*.parquet"
- config_name: "el-IN"
data_files:
- split: train
path: "data/el-IN/*.parquet"
- config_name: "el-IO"
data_files:
- split: train
path: "data/el-IO/*.parquet"
- config_name: "el-IR"
data_files:
- split: train
path: "data/el-IR/*.parquet"
- config_name: "el-IS"
data_files:
- split: train
path: "data/el-IS/*.parquet"
- config_name: "el-IT"
data_files:
- split: train
path: "data/el-IT/*.parquet"
- config_name: "el-LY"
data_files:
- split: train
path: "data/el-LY/*.parquet"
- config_name: "el-ME"
data_files:
- split: train
path: "data/el-ME/*.parquet"
- config_name: "el-MK"
data_files:
- split: train
path: "data/el-MK/*.parquet"
- config_name: "el-ML"
data_files:
- split: train
path: "data/el-ML/*.parquet"
- config_name: "el-MX"
data_files:
- split: train
path: "data/el-MX/*.parquet"
- config_name: "el-NL"
data_files:
- split: train
path: "data/el-NL/*.parquet"
- config_name: "el-NO"
data_files:
- split: train
path: "data/el-NO/*.parquet"
- config_name: "el-NZ"
data_files:
- split: train
path: "data/el-NZ/*.parquet"
- config_name: "el-PL"
data_files:
- split: train
path: "data/el-PL/*.parquet"
- config_name: "el-PM"
data_files:
- split: train
path: "data/el-PM/*.parquet"
- config_name: "el-PO"
data_files:
- split: train
path: "data/el-PO/*.parquet"
- config_name: "el-PT"
data_files:
- split: train
path: "data/el-PT/*.parquet"
- config_name: "el-RO"
data_files:
- split: train
path: "data/el-RO/*.parquet"
- config_name: "el-RS"
data_files:
- split: train
path: "data/el-RS/*.parquet"
- config_name: "el-RU"
data_files:
- split: train
path: "data/el-RU/*.parquet"
- config_name: "el-SE"
data_files:
- split: train
path: "data/el-SE/*.parquet"
- config_name: "el-SG"
data_files:
- split: train
path: "data/el-SG/*.parquet"
- config_name: "el-SK"
data_files:
- split: train
path: "data/el-SK/*.parquet"
- config_name: "el-ST"
data_files:
- split: train
path: "data/el-ST/*.parquet"
- config_name: "el-TH"
data_files:
- split: train
path: "data/el-TH/*.parquet"
- config_name: "el-TK"
data_files:
- split: train
path: "data/el-TK/*.parquet"
- config_name: "el-TL"
data_files:
- split: train
path: "data/el-TL/*.parquet"
- config_name: "el-TO"
data_files:
- split: train
path: "data/el-TO/*.parquet"
- config_name: "el-TR"
data_files:
- split: train
path: "data/el-TR/*.parquet"
- config_name: "el-TV"
data_files:
- split: train
path: "data/el-TV/*.parquet"
- config_name: "el-TW"
data_files:
- split: train
path: "data/el-TW/*.parquet"
- config_name: "el-UA"
data_files:
- split: train
path: "data/el-UA/*.parquet"
- config_name: "el-US"
data_files:
- split: train
path: "data/el-US/*.parquet"
- config_name: "el-WS"
data_files:
- split: train
path: "data/el-WS/*.parquet"
- config_name: "el-XX"
data_files:
- split: train
path: "data/el-XX/*.parquet"
- config_name: "en-AA"
data_files:
- split: train
path: "data/en-AA/*.parquet"
- config_name: "en-AC"
data_files:
- split: train
path: "data/en-AC/*.parquet"
- config_name: "en-AD"
data_files:
- split: train
path: "data/en-AD/*.parquet"
- config_name: "en-AE"
data_files:
- split: train
path: "data/en-AE/*.parquet"
- config_name: "en-AF"
data_files:
- split: train
path: "data/en-AF/*.parquet"
- config_name: "en-AG"
data_files:
- split: train
path: "data/en-AG/*.parquet"
- config_name: "en-AI"
data_files:
- split: train
path: "data/en-AI/*.parquet"
- config_name: "en-AL"
data_files:
- split: train
path: "data/en-AL/*.parquet"
- config_name: "en-AM"
data_files:
- split: train
path: "data/en-AM/*.parquet"
- config_name: "en-AN"
data_files:
- split: train
path: "data/en-AN/*.parquet"
- config_name: "en-AO"
data_files:
- split: train
path: "data/en-AO/*.parquet"
- config_name: "en-AP"
data_files:
- split: train
path: "data/en-AP/*.parquet"
- config_name: "en-AQ"
data_files:
- split: train
path: "data/en-AQ/*.parquet"
- config_name: "en-AR"
data_files:
- split: train
path: "data/en-AR/*.parquet"
- config_name: "en-AS"
data_files:
- split: train
path: "data/en-AS/*.parquet"
- config_name: "en-AT"
data_files:
- split: train
path: "data/en-AT/*.parquet"
- config_name: "en-AU"
data_files:
- split: train
path: "data/en-AU/*.parquet"
- config_name: "en-AW"
data_files:
- split: train
path: "data/en-AW/*.parquet"
- config_name: "en-AX"
data_files:
- split: train
path: "data/en-AX/*.parquet"
- config_name: "en-AZ"
data_files:
- split: train
path: "data/en-AZ/*.parquet"
- config_name: "en-BA"
data_files:
- split: train
path: "data/en-BA/*.parquet"
- config_name: "en-BB"
data_files:
- split: train
path: "data/en-BB/*.parquet"
- config_name: "en-BD"
data_files:
- split: train
path: "data/en-BD/*.parquet"
- config_name: "en-BE"
data_files:
- split: train
path: "data/en-BE/*.parquet"
- config_name: "en-BF"
data_files:
- split: train
path: "data/en-BF/*.parquet"
- config_name: "en-BG"
data_files:
- split: train
path: "data/en-BG/*.parquet"
- config_name: "en-BH"
data_files:
- split: train
path: "data/en-BH/*.parquet"
- config_name: "en-BI"
data_files:
- split: train
path: "data/en-BI/*.parquet"
- config_name: "en-BJ"
data_files:
- split: train
path: "data/en-BJ/*.parquet"
- config_name: "en-BL"
data_files:
- split: train
path: "data/en-BL/*.parquet"
- config_name: "en-BM"
data_files:
- split: train
path: "data/en-BM/*.parquet"
- config_name: "en-BN"
data_files:
- split: train
path: "data/en-BN/*.parquet"
- config_name: "en-BO"
data_files:
- split: train
path: "data/en-BO/*.parquet"
- config_name: "en-BQ"
data_files:
- split: train
path: "data/en-BQ/*.parquet"
- config_name: "en-BR"
data_files:
- split: train
path: "data/en-BR/*.parquet"
- config_name: "en-BS"
data_files:
- split: train
path: "data/en-BS/*.parquet"
- config_name: "en-BT"
data_files:
- split: train
path: "data/en-BT/*.parquet"
- config_name: "en-BW"
data_files:
- split: train
path: "data/en-BW/*.parquet"
- config_name: "en-BY"
data_files:
- split: train
path: "data/en-BY/*.parquet"
- config_name: "en-BZ"
data_files:
- split: train
path: "data/en-BZ/*.parquet"
- config_name: "en-CA"
data_files:
- split: train
path: "data/en-CA/*.parquet"
- config_name: "en-CB"
data_files:
- split: train
path: "data/en-CB/*.parquet"
- config_name: "en-CC"
data_files:
- split: train
path: "data/en-CC/*.parquet"
- config_name: "en-CD"
data_files:
- split: train
path: "data/en-CD/*.parquet"
- config_name: "en-CE"
data_files:
- split: train
path: "data/en-CE/*.parquet"
- config_name: "en-CF"
data_files:
- split: train
path: "data/en-CF/*.parquet"
- config_name: "en-CG"
data_files:
- split: train
path: "data/en-CG/*.parquet"
- config_name: "en-CH"
data_files:
- split: train
path: "data/en-CH/*.parquet"
- config_name: "en-CI"
data_files:
- split: train
path: "data/en-CI/*.parquet"
- config_name: "en-CK"
data_files:
- split: train
path: "data/en-CK/*.parquet"
- config_name: "en-CL"
data_files:
- split: train
path: "data/en-CL/*.parquet"
- config_name: "en-CM"
data_files:
- split: train
path: "data/en-CM/*.parquet"
- config_name: "en-CN"
data_files:
- split: train
path: "data/en-CN/*.parquet"
- config_name: "en-CO"
data_files:
- split: train
path: "data/en-CO/*.parquet"
- config_name: "en-CR"
data_files:
- split: train
path: "data/en-CR/*.parquet"
- config_name: "en-CU"
data_files:
- split: train
path: "data/en-CU/*.parquet"
- config_name: "en-CV"
data_files:
- split: train
path: "data/en-CV/*.parquet"
- config_name: "en-CW"
data_files:
- split: train
path: "data/en-CW/*.parquet"
- config_name: "en-CX"
data_files:
- split: train
path: "data/en-CX/*.parquet"
- config_name: "en-CY"
data_files:
- split: train
path: "data/en-CY/*.parquet"
- config_name: "en-CZ"
data_files:
- split: train
path: "data/en-CZ/*.parquet"
- config_name: "en-DA"
data_files:
- split: train
path: "data/en-DA/*.parquet"
- config_name: "en-DE"
data_files:
- split: train
path: "data/en-DE/*.parquet"
- config_name: "en-DJ"
data_files:
- split: train
path: "data/en-DJ/*.parquet"
- config_name: "en-DK"
data_files:
- split: train
path: "data/en-DK/*.parquet"
- config_name: "en-DM"
data_files:
- split: train
path: "data/en-DM/*.parquet"
- config_name: "en-DO"
data_files:
- split: train
path: "data/en-DO/*.parquet"
- config_name: "en-DR"
data_files:
- split: train
path: "data/en-DR/*.parquet"
- config_name: "en-DX"
data_files:
- split: train
path: "data/en-DX/*.parquet"
- config_name: "en-DZ"
data_files:
- split: train
path: "data/en-DZ/*.parquet"
- config_name: "en-EC"
data_files:
- split: train
path: "data/en-EC/*.parquet"
- config_name: "en-EE"
data_files:
- split: train
path: "data/en-EE/*.parquet"
- config_name: "en-EG"
data_files:
- split: train
path: "data/en-EG/*.parquet"
- config_name: "en-EH"
data_files:
- split: train
path: "data/en-EH/*.parquet"
- config_name: "en-EI"
data_files:
- split: train
path: "data/en-EI/*.parquet"
- config_name: "en-EM"
data_files:
- split: train
path: "data/en-EM/*.parquet"
- config_name: "en-EN"
data_files:
- split: train
path: "data/en-EN/*.parquet"
- config_name: "en-ES"
data_files:
- split: train
path: "data/en-ES/*.parquet"
- config_name: "en-ET"
data_files:
- split: train
path: "data/en-ET/*.parquet"
- config_name: "en-EU"
data_files:
- split: train
path: "data/en-EU/*.parquet"
- config_name: "en-EX"
data_files:
- split: train
path: "data/en-EX/*.parquet"
- config_name: "en-FA"
data_files:
- split: train
path: "data/en-FA/*.parquet"
- config_name: "en-FI"
data_files:
- split: train
path: "data/en-FI/*.parquet"
- config_name: "en-FJ"
data_files:
- split: train
path: "data/en-FJ/*.parquet"
- config_name: "en-FL"
data_files:
- split: train
path: "data/en-FL/*.parquet"
- config_name: "en-FM"
data_files:
- split: train
path: "data/en-FM/*.parquet"
- config_name: "en-FO"
data_files:
- split: train
path: "data/en-FO/*.parquet"
- config_name: "en-FP"
data_files:
- split: train
path: "data/en-FP/*.parquet"
- config_name: "en-FR"
data_files:
- split: train
path: "data/en-FR/*.parquet"
- config_name: "en-GA"
data_files:
- split: train
path: "data/en-GA/*.parquet"
- config_name: "en-GB"
data_files:
- split: train
path: "data/en-GB/*.parquet"
- config_name: "en-GD"
data_files:
- split: train
path: "data/en-GD/*.parquet"
- config_name: "en-GE"
data_files:
- split: train
path: "data/en-GE/*.parquet"
- config_name: "en-GF"
data_files:
- split: train
path: "data/en-GF/*.parquet"
- config_name: "en-GG"
data_files:
- split: train
path: "data/en-GG/*.parquet"
- config_name: "en-GH"
data_files:
- split: train
path: "data/en-GH/*.parquet"
- config_name: "en-GI"
data_files:
- split: train
path: "data/en-GI/*.parquet"
- config_name: "en-GL"
data_files:
- split: train
path: "data/en-GL/*.parquet"
- config_name: "en-GM"
data_files:
- split: train
path: "data/en-GM/*.parquet"
- config_name: "en-GN"
data_files:
- split: train
path: "data/en-GN/*.parquet"
- config_name: "en-GO"
data_files:
- split: train
path: "data/en-GO/*.parquet"
- config_name: "en-GP"
data_files:
- split: train
path: "data/en-GP/*.parquet"
- config_name: "en-GQ"
data_files:
- split: train
path: "data/en-GQ/*.parquet"
- config_name: "en-GR"
data_files:
- split: train
path: "data/en-GR/*.parquet"
- config_name: "en-GS"
data_files:
- split: train
path: "data/en-GS/*.parquet"
- config_name: "en-GT"
data_files:
- split: train
path: "data/en-GT/*.parquet"
- config_name: "en-GU"
data_files:
- split: train
path: "data/en-GU/*.parquet"
- config_name: "en-GW"
data_files:
- split: train
path: "data/en-GW/*.parquet"
- config_name: "en-GX"
data_files:
- split: train
path: "data/en-GX/*.parquet"
- config_name: "en-GY"
data_files:
- split: train
path: "data/en-GY/*.parquet"
- config_name: "en-HE"
data_files:
- split: train
path: "data/en-HE/*.parquet"
- config_name: "en-HK"
data_files:
- split: train
path: "data/en-HK/*.parquet"
- config_name: "en-HN"
data_files:
- split: train
path: "data/en-HN/*.parquet"
- config_name: "en-HQ"
data_files:
- split: train
path: "data/en-HQ/*.parquet"
- config_name: "en-HR"
data_files:
- split: train
path: "data/en-HR/*.parquet"
- config_name: "en-HT"
data_files:
- split: train
path: "data/en-HT/*.parquet"
- config_name: "en-HU"
data_files:
- split: train
path: "data/en-HU/*.parquet"
- config_name: "en-IC"
data_files:
- split: train
path: "data/en-IC/*.parquet"
- config_name: "en-ID"
data_files:
- split: train
path: "data/en-ID/*.parquet"
- config_name: "en-IE"
data_files:
- split: train
path: "data/en-IE/*.parquet"
- config_name: "en-IL"
data_files:
- split: train
path: "data/en-IL/*.parquet"
- config_name: "en-IM"
data_files:
- split: train
path: "data/en-IM/*.parquet"
- config_name: "en-IN"
data_files:
- split: train
path: "data/en-IN/*.parquet"
- config_name: "en-IO"
data_files:
- split: train
path: "data/en-IO/*.parquet"
- config_name: "en-IQ"
data_files:
- split: train
path: "data/en-IQ/*.parquet"
- config_name: "en-IR"
data_files:
- split: train
path: "data/en-IR/*.parquet"
- config_name: "en-IS"
data_files:
- split: train
path: "data/en-IS/*.parquet"
- config_name: "en-IT"
data_files:
- split: train
path: "data/en-IT/*.parquet"
- config_name: "en-IX"
data_files:
- split: train
path: "data/en-IX/*.parquet"
- config_name: "en-JA"
data_files:
- split: train
path: "data/en-JA/*.parquet"
- config_name: "en-JE"
data_files:
- split: train
path: "data/en-JE/*.parquet"
- config_name: "en-JG"
data_files:
- split: train
path: "data/en-JG/*.parquet"
- config_name: "en-JM"
data_files:
- split: train
path: "data/en-JM/*.parquet"
- config_name: "en-JO"
data_files:
- split: train
path: "data/en-JO/*.parquet"
- config_name: "en-JP"
data_files:
- split: train
path: "data/en-JP/*.parquet"
- config_name: "en-KE"
data_files:
- split: train
path: "data/en-KE/*.parquet"
- config_name: "en-KG"
data_files:
- split: train
path: "data/en-KG/*.parquet"
- config_name: "en-KH"
data_files:
- split: train
path: "data/en-KH/*.parquet"
- config_name: "en-KI"
data_files:
- split: train
path: "data/en-KI/*.parquet"
- config_name: "en-KM"
data_files:
- split: train
path: "data/en-KM/*.parquet"
- config_name: "en-KN"
data_files:
- split: train
path: "data/en-KN/*.parquet"
- config_name: "en-KP"
data_files:
- split: train
path: "data/en-KP/*.parquet"
- config_name: "en-KR"
data_files:
- split: train
path: "data/en-KR/*.parquet"
- config_name: "en-KS"
data_files:
- split: train
path: "data/en-KS/*.parquet"
- config_name: "en-KW"
data_files:
- split: train
path: "data/en-KW/*.parquet"
- config_name: "en-KY"
data_files:
- split: train
path: "data/en-KY/*.parquet"
- config_name: "en-KZ"
data_files:
- split: train
path: "data/en-KZ/*.parquet"
- config_name: "en-LA"
data_files:
- split: train
path: "data/en-LA/*.parquet"
- config_name: "en-LB"
data_files:
- split: train
path: "data/en-LB/*.parquet"
- config_name: "en-LC"
data_files:
- split: train
path: "data/en-LC/*.parquet"
- config_name: "en-LI"
data_files:
- split: train
path: "data/en-LI/*.parquet"
- config_name: "en-LK"
data_files:
- split: train
path: "data/en-LK/*.parquet"
- config_name: "en-LM"
data_files:
- split: train
path: "data/en-LM/*.parquet"
- config_name: "en-LO"
data_files:
- split: train
path: "data/en-LO/*.parquet"
- config_name: "en-LP"
data_files:
- split: train
path: "data/en-LP/*.parquet"
- config_name: "en-LR"
data_files:
- split: train
path: "data/en-LR/*.parquet"
- config_name: "en-LS"
data_files:
- split: train
path: "data/en-LS/*.parquet"
- config_name: "en-LT"
data_files:
- split: train
path: "data/en-LT/*.parquet"
- config_name: "en-LU"
data_files:
- split: train
path: "data/en-LU/*.parquet"
- config_name: "en-LV"
data_files:
- split: train
path: "data/en-LV/*.parquet"
- config_name: "en-LY"
data_files:
- split: train
path: "data/en-LY/*.parquet"
- config_name: "en-MA"
data_files:
- split: train
path: "data/en-MA/*.parquet"
- config_name: "en-MC"
data_files:
- split: train
path: "data/en-MC/*.parquet"
- config_name: "en-MD"
data_files:
- split: train
path: "data/en-MD/*.parquet"
- config_name: "en-ME"
data_files:
- split: train
path: "data/en-ME/*.parquet"
- config_name: "en-MF"
data_files:
- split: train
path: "data/en-MF/*.parquet"
- config_name: "en-MG"
data_files:
- split: train
path: "data/en-MG/*.parquet"
- config_name: "en-MH"
data_files:
- split: train
path: "data/en-MH/*.parquet"
- config_name: "en-MI"
data_files:
- split: train
path: "data/en-MI/*.parquet"
- config_name: "en-MK"
data_files:
- split: train
path: "data/en-MK/*.parquet"
- config_name: "en-ML"
data_files:
- split: train
path: "data/en-ML/*.parquet"
- config_name: "en-MM"
data_files:
- split: train
path: "data/en-MM/*.parquet"
- config_name: "en-MN"
data_files:
- split: train
path: "data/en-MN/*.parquet"
- config_name: "en-MO"
data_files:
- split: train
path: "data/en-MO/*.parquet"
- config_name: "en-MP"
data_files:
- split: train
path: "data/en-MP/*.parquet"
- config_name: "en-MQ"
data_files:
- split: train
path: "data/en-MQ/*.parquet"
- config_name: "en-MR"
data_files:
- split: train
path: "data/en-MR/*.parquet"
- config_name: "en-MS"
data_files:
- split: train
path: "data/en-MS/*.parquet"
- config_name: "en-MT"
data_files:
- split: train
path: "data/en-MT/*.parquet"
- config_name: "en-MU"
data_files:
- split: train
path: "data/en-MU/*.parquet"
- config_name: "en-MV"
data_files:
- split: train
path: "data/en-MV/*.parquet"
- config_name: "en-MW"
data_files:
- split: train
path: "data/en-MW/*.parquet"
- config_name: "en-MX"
data_files:
- split: train
path: "data/en-MX/*.parquet"
- config_name: "en-MY"
data_files:
- split: train
path: "data/en-MY/*.parquet"
- config_name: "en-MZ"
data_files:
- split: train
path: "data/en-MZ/*.parquet"
- config_name: "en-NA"
data_files:
- split: train
path: "data/en-NA/*.parquet"
- config_name: "en-NB"
data_files:
- split: train
path: "data/en-NB/*.parquet"
- config_name: "en-NC"
data_files:
- split: train
path: "data/en-NC/*.parquet"
- config_name: "en-ND"
data_files:
- split: train
path: "data/en-ND/*.parquet"
- config_name: "en-NE"
data_files:
- split: train
path: "data/en-NE/*.parquet"
- config_name: "en-NF"
data_files:
- split: train
path: "data/en-NF/*.parquet"
- config_name: "en-NG"
data_files:
- split: train
path: "data/en-NG/*.parquet"
- config_name: "en-NI"
data_files:
- split: train
path: "data/en-NI/*.parquet"
- config_name: "en-NL"
data_files:
- split: train
path: "data/en-NL/*.parquet"
- config_name: "en-NN"
data_files:
- split: train
path: "data/en-NN/*.parquet"
- config_name: "en-NO"
data_files:
- split: train
path: "data/en-NO/*.parquet"
- config_name: "en-NP"
data_files:
- split: train
path: "data/en-NP/*.parquet"
- config_name: "en-NR"
data_files:
- split: train
path: "data/en-NR/*.parquet"
- config_name: "en-NS"
data_files:
- split: train
path: "data/en-NS/*.parquet"
- config_name: "en-NT"
data_files:
- split: train
path: "data/en-NT/*.parquet"
- config_name: "en-NU"
data_files:
- split: train
path: "data/en-NU/*.parquet"
- config_name: "en-NZ"
data_files:
- split: train
path: "data/en-NZ/*.parquet"
- config_name: "en-OC"
data_files:
- split: train
path: "data/en-OC/*.parquet"
- config_name: "en-OE"
data_files:
- split: train
path: "data/en-OE/*.parquet"
- config_name: "en-OJ"
data_files:
- split: train
path: "data/en-OJ/*.parquet"
- config_name: "en-OM"
data_files:
- split: train
path: "data/en-OM/*.parquet"
- config_name: "en-OT"
data_files:
- split: train
path: "data/en-OT/*.parquet"
- config_name: "en-PA"
data_files:
- split: train
path: "data/en-PA/*.parquet"
- config_name: "en-PE"
data_files:
- split: train
path: "data/en-PE/*.parquet"
- config_name: "en-PF"
data_files:
- split: train
path: "data/en-PF/*.parquet"
- config_name: "en-PG"
data_files:
- split: train
path: "data/en-PG/*.parquet"
- config_name: "en-PH"
data_files:
- split: train
path: "data/en-PH/*.parquet"
- config_name: "en-PI"
data_files:
- split: train
path: "data/en-PI/*.parquet"
- config_name: "en-PK"
data_files:
- split: train
path: "data/en-PK/*.parquet"
- config_name: "en-PL"
data_files:
- split: train
path: "data/en-PL/*.parquet"
- config_name: "en-PM"
data_files:
- split: train
path: "data/en-PM/*.parquet"
- config_name: "en-PN"
data_files:
- split: train
path: "data/en-PN/*.parquet"
- config_name: "en-PO"
data_files:
- split: train
path: "data/en-PO/*.parquet"
- config_name: "en-PR"
data_files:
- split: train
path: "data/en-PR/*.parquet"
- config_name: "en-PS"
data_files:
- split: train
path: "data/en-PS/*.parquet"
- config_name: "en-PT"
data_files:
- split: train
path: "data/en-PT/*.parquet"
- config_name: "en-PW"
data_files:
- split: train
path: "data/en-PW/*.parquet"
- config_name: "en-PY"
data_files:
- split: train
path: "data/en-PY/*.parquet"
- config_name: "en-QA"
data_files:
- split: train
path: "data/en-QA/*.parquet"
- config_name: "en-RE"
data_files:
- split: train
path: "data/en-RE/*.parquet"
- config_name: "en-RO"
data_files:
- split: train
path: "data/en-RO/*.parquet"
- config_name: "en-RS"
data_files:
- split: train
path: "data/en-RS/*.parquet"
- config_name: "en-RU"
data_files:
- split: train
path: "data/en-RU/*.parquet"
- config_name: "en-RW"
data_files:
- split: train
path: "data/en-RW/*.parquet"
- config_name: "en-SA"
data_files:
- split: train
path: "data/en-SA/*.parquet"
- config_name: "en-SB"
data_files:
- split: train
path: "data/en-SB/*.parquet"
- config_name: "en-SC"
data_files:
- split: train
path: "data/en-SC/*.parquet"
- config_name: "en-SD"
data_files:
- split: train
path: "data/en-SD/*.parquet"
- config_name: "en-SE"
data_files:
- split: train
path: "data/en-SE/*.parquet"
- config_name: "en-SG"
data_files:
- split: train
path: "data/en-SG/*.parquet"
- config_name: "en-SH"
data_files:
- split: train
path: "data/en-SH/*.parquet"
- config_name: "en-SI"
data_files:
- split: train
path: "data/en-SI/*.parquet"
- config_name: "en-SJ"
data_files:
- split: train
path: "data/en-SJ/*.parquet"
- config_name: "en-SK"
data_files:
- split: train
path: "data/en-SK/*.parquet"
- config_name: "en-SL"
data_files:
- split: train
path: "data/en-SL/*.parquet"
- config_name: "en-SM"
data_files:
- split: train
path: "data/en-SM/*.parquet"
- config_name: "en-SN"
data_files:
- split: train
path: "data/en-SN/*.parquet"
- config_name: "en-SO"
data_files:
- split: train
path: "data/en-SO/*.parquet"
- config_name: "en-SP"
data_files:
- split: train
path: "data/en-SP/*.parquet"
- config_name: "en-SR"
data_files:
- split: train
path: "data/en-SR/*.parquet"
- config_name: "en-SS"
data_files:
- split: train
path: "data/en-SS/*.parquet"
- config_name: "en-ST"
data_files:
- split: train
path: "data/en-ST/*.parquet"
- config_name: "en-SV"
data_files:
- split: train
path: "data/en-SV/*.parquet"
- config_name: "en-SW"
data_files:
- split: train
path: "data/en-SW/*.parquet"
- config_name: "en-SX"
data_files:
- split: train
path: "data/en-SX/*.parquet"
- config_name: "en-SY"
data_files:
- split: train
path: "data/en-SY/*.parquet"
- config_name: "en-SZ"
data_files:
- split: train
path: "data/en-SZ/*.parquet"
- config_name: "en-TC"
data_files:
- split: train
path: "data/en-TC/*.parquet"
- config_name: "en-TD"
data_files:
- split: train
path: "data/en-TD/*.parquet"
- config_name: "en-TF"
data_files:
- split: train
path: "data/en-TF/*.parquet"
- config_name: "en-TG"
data_files:
- split: train
path: "data/en-TG/*.parquet"
- config_name: "en-TH"
data_files:
- split: train
path: "data/en-TH/*.parquet"
- config_name: "en-TJ"
data_files:
- split: train
path: "data/en-TJ/*.parquet"
- config_name: "en-TK"
data_files:
- split: train
path: "data/en-TK/*.parquet"
- config_name: "en-TL"
data_files:
- split: train
path: "data/en-TL/*.parquet"
- config_name: "en-TM"
data_files:
- split: train
path: "data/en-TM/*.parquet"
- config_name: "en-TN"
data_files:
- split: train
path: "data/en-TN/*.parquet"
- config_name: "en-TO"
data_files:
- split: train
path: "data/en-TO/*.parquet"
- config_name: "en-TR"
data_files:
- split: train
path: "data/en-TR/*.parquet"
- config_name: "en-TT"
data_files:
- split: train
path: "data/en-TT/*.parquet"
- config_name: "en-TV"
data_files:
- split: train
path: "data/en-TV/*.parquet"
- config_name: "en-TW"
data_files:
- split: train
path: "data/en-TW/*.parquet"
- config_name: "en-TZ"
data_files:
- split: train
path: "data/en-TZ/*.parquet"
- config_name: "en-UA"
data_files:
- split: train
path: "data/en-UA/*.parquet"
- config_name: "en-UG"
data_files:
- split: train
path: "data/en-UG/*.parquet"
- config_name: "en-UK"
data_files:
- split: train
path: "data/en-UK/*.parquet"
- config_name: "en-UM"
data_files:
- split: train
path: "data/en-UM/*.parquet"
- config_name: "en-UN"
data_files:
- split: train
path: "data/en-UN/*.parquet"
- config_name: "en-US"
data_files:
- split: train
path: "data/en-US/*.parquet"
- config_name: "en-UY"
data_files:
- split: train
path: "data/en-UY/*.parquet"
- config_name: "en-UZ"
data_files:
- split: train
path: "data/en-UZ/*.parquet"
- config_name: "en-VA"
data_files:
- split: train
path: "data/en-VA/*.parquet"
- config_name: "en-VC"
data_files:
- split: train
path: "data/en-VC/*.parquet"
- config_name: "en-VE"
data_files:
- split: train
path: "data/en-VE/*.parquet"
- config_name: "en-VG"
data_files:
- split: train
path: "data/en-VG/*.parquet"
- config_name: "en-VI"
data_files:
- split: train
path: "data/en-VI/*.parquet"
- config_name: "en-VN"
data_files:
- split: train
path: "data/en-VN/*.parquet"
- config_name: "en-VR"
data_files:
- split: train
path: "data/en-VR/*.parquet"
- config_name: "en-VU"
data_files:
- split: train
path: "data/en-VU/*.parquet"
- config_name: "en-WA"
data_files:
- split: train
path: "data/en-WA/*.parquet"
- config_name: "en-WF"
data_files:
- split: train
path: "data/en-WF/*.parquet"
- config_name: "en-WI"
data_files:
- split: train
path: "data/en-WI/*.parquet"
- config_name: "en-WP"
data_files:
- split: train
path: "data/en-WP/*.parquet"
- config_name: "en-WR"
data_files:
- split: train
path: "data/en-WR/*.parquet"
- config_name: "en-WS"
data_files:
- split: train
path: "data/en-WS/*.parquet"
- config_name: "en-WW"
data_files:
- split: train
path: "data/en-WW/*.parquet"
- config_name: "en-XA"
data_files:
- split: train
path: "data/en-XA/*.parquet"
- config_name: "en-XB"
data_files:
- split: train
path: "data/en-XB/*.parquet"
- config_name: "en-XE"
data_files:
- split: train
path: "data/en-XE/*.parquet"
- config_name: "en-XI"
data_files:
- split: train
path: "data/en-XI/*.parquet"
- config_name: "en-XK"
data_files:
- split: train
path: "data/en-XK/*.parquet"
- config_name: "en-XL"
data_files:
- split: train
path: "data/en-XL/*.parquet"
- config_name: "en-XM"
data_files:
- split: train
path: "data/en-XM/*.parquet"
- config_name: "en-XX"
data_files:
- split: train
path: "data/en-XX/*.parquet"
- config_name: "en-YA"
data_files:
- split: train
path: "data/en-YA/*.parquet"
- config_name: "en-YE"
data_files:
- split: train
path: "data/en-YE/*.parquet"
- config_name: "en-YT"
data_files:
- split: train
path: "data/en-YT/*.parquet"
- config_name: "en-YU"
data_files:
- split: train
path: "data/en-YU/*.parquet"
- config_name: "en-YY"
data_files:
- split: train
path: "data/en-YY/*.parquet"
- config_name: "en-ZA"
data_files:
- split: train
path: "data/en-ZA/*.parquet"
- config_name: "en-ZH"
data_files:
- split: train
path: "data/en-ZH/*.parquet"
- config_name: "en-ZM"
data_files:
- split: train
path: "data/en-ZM/*.parquet"
- config_name: "en-ZW"
data_files:
- split: train
path: "data/en-ZW/*.parquet"
- config_name: "en-ZZ"
data_files:
- split: train
path: "data/en-ZZ/*.parquet"
- config_name: "eo-AI"
data_files:
- split: train
path: "data/eo-AI/*.parquet"
- config_name: "eo-BE"
data_files:
- split: train
path: "data/eo-BE/*.parquet"
- config_name: "eo-BR"
data_files:
- split: train
path: "data/eo-BR/*.parquet"
- config_name: "eo-BZ"
data_files:
- split: train
path: "data/eo-BZ/*.parquet"
- config_name: "eo-CA"
data_files:
- split: train
path: "data/eo-CA/*.parquet"
- config_name: "eo-CH"
data_files:
- split: train
path: "data/eo-CH/*.parquet"
- config_name: "eo-CL"
data_files:
- split: train
path: "data/eo-CL/*.parquet"
- config_name: "eo-CN"
data_files:
- split: train
path: "data/eo-CN/*.parquet"
- config_name: "eo-CO"
data_files:
- split: train
path: "data/eo-CO/*.parquet"
- config_name: "eo-CZ"
data_files:
- split: train
path: "data/eo-CZ/*.parquet"
- config_name: "eo-DE"
data_files:
- split: train
path: "data/eo-DE/*.parquet"
- config_name: "eo-DK"
data_files:
- split: train
path: "data/eo-DK/*.parquet"
- config_name: "eo-EO"
data_files:
- split: train
path: "data/eo-EO/*.parquet"
- config_name: "eo-EU"
data_files:
- split: train
path: "data/eo-EU/*.parquet"
- config_name: "eo-FR"
data_files:
- split: train
path: "data/eo-FR/*.parquet"
- config_name: "eo-GB"
data_files:
- split: train
path: "data/eo-GB/*.parquet"
- config_name: "eo-HR"
data_files:
- split: train
path: "data/eo-HR/*.parquet"
- config_name: "eo-HU"
data_files:
- split: train
path: "data/eo-HU/*.parquet"
- config_name: "eo-ID"
data_files:
- split: train
path: "data/eo-ID/*.parquet"
- config_name: "eo-IT"
data_files:
- split: train
path: "data/eo-IT/*.parquet"
- config_name: "eo-JP"
data_files:
- split: train
path: "data/eo-JP/*.parquet"
- config_name: "eo-LA"
data_files:
- split: train
path: "data/eo-LA/*.parquet"
- config_name: "eo-PL"
data_files:
- split: train
path: "data/eo-PL/*.parquet"
- config_name: "eo-RO"
data_files:
- split: train
path: "data/eo-RO/*.parquet"
- config_name: "eo-RU"
data_files:
- split: train
path: "data/eo-RU/*.parquet"
- config_name: "eo-SE"
data_files:
- split: train
path: "data/eo-SE/*.parquet"
- config_name: "eo-TK"
data_files:
- split: train
path: "data/eo-TK/*.parquet"
- config_name: "eo-TR"
data_files:
- split: train
path: "data/eo-TR/*.parquet"
- config_name: "eo-TW"
data_files:
- split: train
path: "data/eo-TW/*.parquet"
- config_name: "eo-US"
data_files:
- split: train
path: "data/eo-US/*.parquet"
- config_name: "eo-UY"
data_files:
- split: train
path: "data/eo-UY/*.parquet"
- config_name: "eo-XX"
data_files:
- split: train
path: "data/eo-XX/*.parquet"
- config_name: "es-AC"
data_files:
- split: train
path: "data/es-AC/*.parquet"
- config_name: "es-AD"
data_files:
- split: train
path: "data/es-AD/*.parquet"
- config_name: "es-AE"
data_files:
- split: train
path: "data/es-AE/*.parquet"
- config_name: "es-AG"
data_files:
- split: train
path: "data/es-AG/*.parquet"
- config_name: "es-AI"
data_files:
- split: train
path: "data/es-AI/*.parquet"
- config_name: "es-AL"
data_files:
- split: train
path: "data/es-AL/*.parquet"
- config_name: "es-AM"
data_files:
- split: train
path: "data/es-AM/*.parquet"
- config_name: "es-AN"
data_files:
- split: train
path: "data/es-AN/*.parquet"
- config_name: "es-AO"
data_files:
- split: train
path: "data/es-AO/*.parquet"
- config_name: "es-AQ"
data_files:
- split: train
path: "data/es-AQ/*.parquet"
- config_name: "es-AR"
data_files:
- split: train
path: "data/es-AR/*.parquet"
- config_name: "es-AS"
data_files:
- split: train
path: "data/es-AS/*.parquet"
- config_name: "es-AT"
data_files:
- split: train
path: "data/es-AT/*.parquet"
- config_name: "es-AU"
data_files:
- split: train
path: "data/es-AU/*.parquet"
- config_name: "es-AX"
data_files:
- split: train
path: "data/es-AX/*.parquet"
- config_name: "es-AZ"
data_files:
- split: train
path: "data/es-AZ/*.parquet"
- config_name: "es-BA"
data_files:
- split: train
path: "data/es-BA/*.parquet"
- config_name: "es-BD"
data_files:
- split: train
path: "data/es-BD/*.parquet"
- config_name: "es-BE"
data_files:
- split: train
path: "data/es-BE/*.parquet"
- config_name: "es-BG"
data_files:
- split: train
path: "data/es-BG/*.parquet"
- config_name: "es-BL"
data_files:
- split: train
path: "data/es-BL/*.parquet"
- config_name: "es-BM"
data_files:
- split: train
path: "data/es-BM/*.parquet"
- config_name: "es-BO"
data_files:
- split: train
path: "data/es-BO/*.parquet"
- config_name: "es-BQ"
data_files:
- split: train
path: "data/es-BQ/*.parquet"
- config_name: "es-BR"
data_files:
- split: train
path: "data/es-BR/*.parquet"
- config_name: "es-BS"
data_files:
- split: train
path: "data/es-BS/*.parquet"
- config_name: "es-BY"
data_files:
- split: train
path: "data/es-BY/*.parquet"
- config_name: "es-BZ"
data_files:
- split: train
path: "data/es-BZ/*.parquet"
- config_name: "es-CA"
data_files:
- split: train
path: "data/es-CA/*.parquet"
- config_name: "es-CC"
data_files:
- split: train
path: "data/es-CC/*.parquet"
- config_name: "es-CD"
data_files:
- split: train
path: "data/es-CD/*.parquet"
- config_name: "es-CF"
data_files:
- split: train
path: "data/es-CF/*.parquet"
- config_name: "es-CH"
data_files:
- split: train
path: "data/es-CH/*.parquet"
- config_name: "es-CL"
data_files:
- split: train
path: "data/es-CL/*.parquet"
- config_name: "es-CN"
data_files:
- split: train
path: "data/es-CN/*.parquet"
- config_name: "es-CO"
data_files:
- split: train
path: "data/es-CO/*.parquet"
- config_name: "es-CR"
data_files:
- split: train
path: "data/es-CR/*.parquet"
- config_name: "es-CU"
data_files:
- split: train
path: "data/es-CU/*.parquet"
- config_name: "es-CX"
data_files:
- split: train
path: "data/es-CX/*.parquet"
- config_name: "es-CY"
data_files:
- split: train
path: "data/es-CY/*.parquet"
- config_name: "es-CZ"
data_files:
- split: train
path: "data/es-CZ/*.parquet"
- config_name: "es-DE"
data_files:
- split: train
path: "data/es-DE/*.parquet"
- config_name: "es-DJ"
data_files:
- split: train
path: "data/es-DJ/*.parquet"
- config_name: "es-DK"
data_files:
- split: train
path: "data/es-DK/*.parquet"
- config_name: "es-DO"
data_files:
- split: train
path: "data/es-DO/*.parquet"
- config_name: "es-DZ"
data_files:
- split: train
path: "data/es-DZ/*.parquet"
- config_name: "es-EC"
data_files:
- split: train
path: "data/es-EC/*.parquet"
- config_name: "es-EE"
data_files:
- split: train
path: "data/es-EE/*.parquet"
- config_name: "es-EG"
data_files:
- split: train
path: "data/es-EG/*.parquet"
- config_name: "es-EN"
data_files:
- split: train
path: "data/es-EN/*.parquet"
- config_name: "es-ES"
data_files:
- split: train
path: "data/es-ES/*.parquet"
- config_name: "es-ET"
data_files:
- split: train
path: "data/es-ET/*.parquet"
- config_name: "es-EU"
data_files:
- split: train
path: "data/es-EU/*.parquet"
- config_name: "es-FI"
data_files:
- split: train
path: "data/es-FI/*.parquet"
- config_name: "es-FM"
data_files:
- split: train
path: "data/es-FM/*.parquet"
- config_name: "es-FO"
data_files:
- split: train
path: "data/es-FO/*.parquet"
- config_name: "es-FR"
data_files:
- split: train
path: "data/es-FR/*.parquet"
- config_name: "es-GA"
data_files:
- split: train
path: "data/es-GA/*.parquet"
- config_name: "es-GB"
data_files:
- split: train
path: "data/es-GB/*.parquet"
- config_name: "es-GD"
data_files:
- split: train
path: "data/es-GD/*.parquet"
- config_name: "es-GG"
data_files:
- split: train
path: "data/es-GG/*.parquet"
- config_name: "es-GI"
data_files:
- split: train
path: "data/es-GI/*.parquet"
- config_name: "es-GL"
data_files:
- split: train
path: "data/es-GL/*.parquet"
- config_name: "es-GP"
data_files:
- split: train
path: "data/es-GP/*.parquet"
- config_name: "es-GQ"
data_files:
- split: train
path: "data/es-GQ/*.parquet"
- config_name: "es-GR"
data_files:
- split: train
path: "data/es-GR/*.parquet"
- config_name: "es-GT"
data_files:
- split: train
path: "data/es-GT/*.parquet"
- config_name: "es-HK"
data_files:
- split: train
path: "data/es-HK/*.parquet"
- config_name: "es-HN"
data_files:
- split: train
path: "data/es-HN/*.parquet"
- config_name: "es-HR"
data_files:
- split: train
path: "data/es-HR/*.parquet"
- config_name: "es-HT"
data_files:
- split: train
path: "data/es-HT/*.parquet"
- config_name: "es-HU"
data_files:
- split: train
path: "data/es-HU/*.parquet"
- config_name: "es-IA"
data_files:
- split: train
path: "data/es-IA/*.parquet"
- config_name: "es-ID"
data_files:
- split: train
path: "data/es-ID/*.parquet"
- config_name: "es-IE"
data_files:
- split: train
path: "data/es-IE/*.parquet"
- config_name: "es-IL"
data_files:
- split: train
path: "data/es-IL/*.parquet"
- config_name: "es-IM"
data_files:
- split: train
path: "data/es-IM/*.parquet"
- config_name: "es-IN"
data_files:
- split: train
path: "data/es-IN/*.parquet"
- config_name: "es-IO"
data_files:
- split: train
path: "data/es-IO/*.parquet"
- config_name: "es-IR"
data_files:
- split: train
path: "data/es-IR/*.parquet"
- config_name: "es-IS"
data_files:
- split: train
path: "data/es-IS/*.parquet"
- config_name: "es-IT"
data_files:
- split: train
path: "data/es-IT/*.parquet"
- config_name: "es-JP"
data_files:
- split: train
path: "data/es-JP/*.parquet"
- config_name: "es-KE"
data_files:
- split: train
path: "data/es-KE/*.parquet"
- config_name: "es-KG"
data_files:
- split: train
path: "data/es-KG/*.parquet"
- config_name: "es-KR"
data_files:
- split: train
path: "data/es-KR/*.parquet"
- config_name: "es-KZ"
data_files:
- split: train
path: "data/es-KZ/*.parquet"
- config_name: "es-LA"
data_files:
- split: train
path: "data/es-LA/*.parquet"
- config_name: "es-LB"
data_files:
- split: train
path: "data/es-LB/*.parquet"
- config_name: "es-LC"
data_files:
- split: train
path: "data/es-LC/*.parquet"
- config_name: "es-LI"
data_files:
- split: train
path: "data/es-LI/*.parquet"
- config_name: "es-LK"
data_files:
- split: train
path: "data/es-LK/*.parquet"
- config_name: "es-LT"
data_files:
- split: train
path: "data/es-LT/*.parquet"
- config_name: "es-LU"
data_files:
- split: train
path: "data/es-LU/*.parquet"
- config_name: "es-LV"
data_files:
- split: train
path: "data/es-LV/*.parquet"
- config_name: "es-LX"
data_files:
- split: train
path: "data/es-LX/*.parquet"
- config_name: "es-LY"
data_files:
- split: train
path: "data/es-LY/*.parquet"
- config_name: "es-MA"
data_files:
- split: train
path: "data/es-MA/*.parquet"
- config_name: "es-MC"
data_files:
- split: train
path: "data/es-MC/*.parquet"
- config_name: "es-MD"
data_files:
- split: train
path: "data/es-MD/*.parquet"
- config_name: "es-ME"
data_files:
- split: train
path: "data/es-ME/*.parquet"
- config_name: "es-MF"
data_files:
- split: train
path: "data/es-MF/*.parquet"
- config_name: "es-MK"
data_files:
- split: train
path: "data/es-MK/*.parquet"
- config_name: "es-ML"
data_files:
- split: train
path: "data/es-ML/*.parquet"
- config_name: "es-MQ"
data_files:
- split: train
path: "data/es-MQ/*.parquet"
- config_name: "es-MS"
data_files:
- split: train
path: "data/es-MS/*.parquet"
- config_name: "es-MX"
data_files:
- split: train
path: "data/es-MX/*.parquet"
- config_name: "es-MY"
data_files:
- split: train
path: "data/es-MY/*.parquet"
- config_name: "es-NA"
data_files:
- split: train
path: "data/es-NA/*.parquet"
- config_name: "es-NG"
data_files:
- split: train
path: "data/es-NG/*.parquet"
- config_name: "es-NI"
data_files:
- split: train
path: "data/es-NI/*.parquet"
- config_name: "es-NL"
data_files:
- split: train
path: "data/es-NL/*.parquet"
- config_name: "es-NO"
data_files:
- split: train
path: "data/es-NO/*.parquet"
- config_name: "es-NU"
data_files:
- split: train
path: "data/es-NU/*.parquet"
- config_name: "es-NZ"
data_files:
- split: train
path: "data/es-NZ/*.parquet"
- config_name: "es-PA"
data_files:
- split: train
path: "data/es-PA/*.parquet"
- config_name: "es-PE"
data_files:
- split: train
path: "data/es-PE/*.parquet"
- config_name: "es-PH"
data_files:
- split: train
path: "data/es-PH/*.parquet"
- config_name: "es-PK"
data_files:
- split: train
path: "data/es-PK/*.parquet"
- config_name: "es-PL"
data_files:
- split: train
path: "data/es-PL/*.parquet"
- config_name: "es-PM"
data_files:
- split: train
path: "data/es-PM/*.parquet"
- config_name: "es-PR"
data_files:
- split: train
path: "data/es-PR/*.parquet"
- config_name: "es-PT"
data_files:
- split: train
path: "data/es-PT/*.parquet"
- config_name: "es-PW"
data_files:
- split: train
path: "data/es-PW/*.parquet"
- config_name: "es-PY"
data_files:
- split: train
path: "data/es-PY/*.parquet"
- config_name: "es-RK"
data_files:
- split: train
path: "data/es-RK/*.parquet"
- config_name: "es-RO"
data_files:
- split: train
path: "data/es-RO/*.parquet"
- config_name: "es-RS"
data_files:
- split: train
path: "data/es-RS/*.parquet"
- config_name: "es-RU"
data_files:
- split: train
path: "data/es-RU/*.parquet"
- config_name: "es-SA"
data_files:
- split: train
path: "data/es-SA/*.parquet"
- config_name: "es-SC"
data_files:
- split: train
path: "data/es-SC/*.parquet"
- config_name: "es-SE"
data_files:
- split: train
path: "data/es-SE/*.parquet"
- config_name: "es-SG"
data_files:
- split: train
path: "data/es-SG/*.parquet"
- config_name: "es-SH"
data_files:
- split: train
path: "data/es-SH/*.parquet"
- config_name: "es-SI"
data_files:
- split: train
path: "data/es-SI/*.parquet"
- config_name: "es-SK"
data_files:
- split: train
path: "data/es-SK/*.parquet"
- config_name: "es-SN"
data_files:
- split: train
path: "data/es-SN/*.parquet"
- config_name: "es-SO"
data_files:
- split: train
path: "data/es-SO/*.parquet"
- config_name: "es-SP"
data_files:
- split: train
path: "data/es-SP/*.parquet"
- config_name: "es-ST"
data_files:
- split: train
path: "data/es-ST/*.parquet"
- config_name: "es-SV"
data_files:
- split: train
path: "data/es-SV/*.parquet"
- config_name: "es-TH"
data_files:
- split: train
path: "data/es-TH/*.parquet"
- config_name: "es-TK"
data_files:
- split: train
path: "data/es-TK/*.parquet"
- config_name: "es-TL"
data_files:
- split: train
path: "data/es-TL/*.parquet"
- config_name: "es-TN"
data_files:
- split: train
path: "data/es-TN/*.parquet"
- config_name: "es-TO"
data_files:
- split: train
path: "data/es-TO/*.parquet"
- config_name: "es-TR"
data_files:
- split: train
path: "data/es-TR/*.parquet"
- config_name: "es-TV"
data_files:
- split: train
path: "data/es-TV/*.parquet"
- config_name: "es-TW"
data_files:
- split: train
path: "data/es-TW/*.parquet"
- config_name: "es-TZ"
data_files:
- split: train
path: "data/es-TZ/*.parquet"
- config_name: "es-UA"
data_files:
- split: train
path: "data/es-UA/*.parquet"
- config_name: "es-UK"
data_files:
- split: train
path: "data/es-UK/*.parquet"
- config_name: "es-UM"
data_files:
- split: train
path: "data/es-UM/*.parquet"
- config_name: "es-UN"
data_files:
- split: train
path: "data/es-UN/*.parquet"
- config_name: "es-US"
data_files:
- split: train
path: "data/es-US/*.parquet"
- config_name: "es-UY"
data_files:
- split: train
path: "data/es-UY/*.parquet"
- config_name: "es-UZ"
data_files:
- split: train
path: "data/es-UZ/*.parquet"
- config_name: "es-VA"
data_files:
- split: train
path: "data/es-VA/*.parquet"
- config_name: "es-VC"
data_files:
- split: train
path: "data/es-VC/*.parquet"
- config_name: "es-VE"
data_files:
- split: train
path: "data/es-VE/*.parquet"
- config_name: "es-VG"
data_files:
- split: train
path: "data/es-VG/*.parquet"
- config_name: "es-VI"
data_files:
- split: train
path: "data/es-VI/*.parquet"
- config_name: "es-VN"
data_files:
- split: train
path: "data/es-VN/*.parquet"
- config_name: "es-VU"
data_files:
- split: train
path: "data/es-VU/*.parquet"
- config_name: "es-WF"
data_files:
- split: train
path: "data/es-WF/*.parquet"
- config_name: "es-WS"
data_files:
- split: train
path: "data/es-WS/*.parquet"
- config_name: "es-WW"
data_files:
- split: train
path: "data/es-WW/*.parquet"
- config_name: "es-XL"
data_files:
- split: train
path: "data/es-XL/*.parquet"
- config_name: "es-XM"
data_files:
- split: train
path: "data/es-XM/*.parquet"
- config_name: "es-XX"
data_files:
- split: train
path: "data/es-XX/*.parquet"
- config_name: "es-ZA"
data_files:
- split: train
path: "data/es-ZA/*.parquet"
- config_name: "es-ZB"
data_files:
- split: train
path: "data/es-ZB/*.parquet"
- config_name: "es-ZW"
data_files:
- split: train
path: "data/es-ZW/*.parquet"
- config_name: "es-ZZ"
data_files:
- split: train
path: "data/es-ZZ/*.parquet"
- config_name: "et-AL"
data_files:
- split: train
path: "data/et-AL/*.parquet"
- config_name: "et-AT"
data_files:
- split: train
path: "data/et-AT/*.parquet"
- config_name: "et-BR"
data_files:
- split: train
path: "data/et-BR/*.parquet"
- config_name: "et-CA"
data_files:
- split: train
path: "data/et-CA/*.parquet"
- config_name: "et-CC"
data_files:
- split: train
path: "data/et-CC/*.parquet"
- config_name: "et-CF"
data_files:
- split: train
path: "data/et-CF/*.parquet"
- config_name: "et-CH"
data_files:
- split: train
path: "data/et-CH/*.parquet"
- config_name: "et-CN"
data_files:
- split: train
path: "data/et-CN/*.parquet"
- config_name: "et-CO"
data_files:
- split: train
path: "data/et-CO/*.parquet"
- config_name: "et-DE"
data_files:
- split: train
path: "data/et-DE/*.parquet"
- config_name: "et-DO"
data_files:
- split: train
path: "data/et-DO/*.parquet"
- config_name: "et-EE"
data_files:
- split: train
path: "data/et-EE/*.parquet"
- config_name: "et-ES"
data_files:
- split: train
path: "data/et-ES/*.parquet"
- config_name: "et-ET"
data_files:
- split: train
path: "data/et-ET/*.parquet"
- config_name: "et-EU"
data_files:
- split: train
path: "data/et-EU/*.parquet"
- config_name: "et-FI"
data_files:
- split: train
path: "data/et-FI/*.parquet"
- config_name: "et-FM"
data_files:
- split: train
path: "data/et-FM/*.parquet"
- config_name: "et-FR"
data_files:
- split: train
path: "data/et-FR/*.parquet"
- config_name: "et-GB"
data_files:
- split: train
path: "data/et-GB/*.parquet"
- config_name: "et-HU"
data_files:
- split: train
path: "data/et-HU/*.parquet"
- config_name: "et-IN"
data_files:
- split: train
path: "data/et-IN/*.parquet"
- config_name: "et-IO"
data_files:
- split: train
path: "data/et-IO/*.parquet"
- config_name: "et-IT"
data_files:
- split: train
path: "data/et-IT/*.parquet"
- config_name: "et-LT"
data_files:
- split: train
path: "data/et-LT/*.parquet"
- config_name: "et-LV"
data_files:
- split: train
path: "data/et-LV/*.parquet"
- config_name: "et-ME"
data_files:
- split: train
path: "data/et-ME/*.parquet"
- config_name: "et-NL"
data_files:
- split: train
path: "data/et-NL/*.parquet"
- config_name: "et-NZ"
data_files:
- split: train
path: "data/et-NZ/*.parquet"
- config_name: "et-PL"
data_files:
- split: train
path: "data/et-PL/*.parquet"
- config_name: "et-RU"
data_files:
- split: train
path: "data/et-RU/*.parquet"
- config_name: "et-SE"
data_files:
- split: train
path: "data/et-SE/*.parquet"
- config_name: "et-SH"
data_files:
- split: train
path: "data/et-SH/*.parquet"
- config_name: "et-SI"
data_files:
- split: train
path: "data/et-SI/*.parquet"
- config_name: "et-ST"
data_files:
- split: train
path: "data/et-ST/*.parquet"
- config_name: "et-TV"
data_files:
- split: train
path: "data/et-TV/*.parquet"
- config_name: "et-UA"
data_files:
- split: train
path: "data/et-UA/*.parquet"
- config_name: "et-US"
data_files:
- split: train
path: "data/et-US/*.parquet"
- config_name: "et-WS"
data_files:
- split: train
path: "data/et-WS/*.parquet"
- config_name: "et-XX"
data_files:
- split: train
path: "data/et-XX/*.parquet"
- config_name: "et-ZA"
data_files:
- split: train
path: "data/et-ZA/*.parquet"
- config_name: "eu-AT"
data_files:
- split: train
path: "data/eu-AT/*.parquet"
- config_name: "eu-CN"
data_files:
- split: train
path: "data/eu-CN/*.parquet"
- config_name: "eu-CZ"
data_files:
- split: train
path: "data/eu-CZ/*.parquet"
- config_name: "eu-DE"
data_files:
- split: train
path: "data/eu-DE/*.parquet"
- config_name: "eu-EH"
data_files:
- split: train
path: "data/eu-EH/*.parquet"
- config_name: "eu-ES"
data_files:
- split: train
path: "data/eu-ES/*.parquet"
- config_name: "eu-EU"
data_files:
- split: train
path: "data/eu-EU/*.parquet"
- config_name: "eu-FR"
data_files:
- split: train
path: "data/eu-FR/*.parquet"
- config_name: "eu-GB"
data_files:
- split: train
path: "data/eu-GB/*.parquet"
- config_name: "eu-IE"
data_files:
- split: train
path: "data/eu-IE/*.parquet"
- config_name: "eu-IT"
data_files:
- split: train
path: "data/eu-IT/*.parquet"
- config_name: "eu-LA"
data_files:
- split: train
path: "data/eu-LA/*.parquet"
- config_name: "eu-PM"
data_files:
- split: train
path: "data/eu-PM/*.parquet"
- config_name: "eu-PT"
data_files:
- split: train
path: "data/eu-PT/*.parquet"
- config_name: "eu-TV"
data_files:
- split: train
path: "data/eu-TV/*.parquet"
- config_name: "eu-UA"
data_files:
- split: train
path: "data/eu-UA/*.parquet"
- config_name: "eu-US"
data_files:
- split: train
path: "data/eu-US/*.parquet"
- config_name: "eu-XX"
data_files:
- split: train
path: "data/eu-XX/*.parquet"
- config_name: "fa-AA"
data_files:
- split: train
path: "data/fa-AA/*.parquet"
- config_name: "fa-AF"
data_files:
- split: train
path: "data/fa-AF/*.parquet"
- config_name: "fa-AI"
data_files:
- split: train
path: "data/fa-AI/*.parquet"
- config_name: "fa-AM"
data_files:
- split: train
path: "data/fa-AM/*.parquet"
- config_name: "fa-AT"
data_files:
- split: train
path: "data/fa-AT/*.parquet"
- config_name: "fa-AU"
data_files:
- split: train
path: "data/fa-AU/*.parquet"
- config_name: "fa-AZ"
data_files:
- split: train
path: "data/fa-AZ/*.parquet"
- config_name: "fa-BE"
data_files:
- split: train
path: "data/fa-BE/*.parquet"
- config_name: "fa-BR"
data_files:
- split: train
path: "data/fa-BR/*.parquet"
- config_name: "fa-BZ"
data_files:
- split: train
path: "data/fa-BZ/*.parquet"
- config_name: "fa-CA"
data_files:
- split: train
path: "data/fa-CA/*.parquet"
- config_name: "fa-CC"
data_files:
- split: train
path: "data/fa-CC/*.parquet"
- config_name: "fa-CF"
data_files:
- split: train
path: "data/fa-CF/*.parquet"
- config_name: "fa-CH"
data_files:
- split: train
path: "data/fa-CH/*.parquet"
- config_name: "fa-CN"
data_files:
- split: train
path: "data/fa-CN/*.parquet"
- config_name: "fa-CO"
data_files:
- split: train
path: "data/fa-CO/*.parquet"
- config_name: "fa-CZ"
data_files:
- split: train
path: "data/fa-CZ/*.parquet"
- config_name: "fa-DE"
data_files:
- split: train
path: "data/fa-DE/*.parquet"
- config_name: "fa-DJ"
data_files:
- split: train
path: "data/fa-DJ/*.parquet"
- config_name: "fa-DK"
data_files:
- split: train
path: "data/fa-DK/*.parquet"
- config_name: "fa-EG"
data_files:
- split: train
path: "data/fa-EG/*.parquet"
- config_name: "fa-ES"
data_files:
- split: train
path: "data/fa-ES/*.parquet"
- config_name: "fa-ET"
data_files:
- split: train
path: "data/fa-ET/*.parquet"
- config_name: "fa-EU"
data_files:
- split: train
path: "data/fa-EU/*.parquet"
- config_name: "fa-FA"
data_files:
- split: train
path: "data/fa-FA/*.parquet"
- config_name: "fa-FI"
data_files:
- split: train
path: "data/fa-FI/*.parquet"
- config_name: "fa-FM"
data_files:
- split: train
path: "data/fa-FM/*.parquet"
- config_name: "fa-FR"
data_files:
- split: train
path: "data/fa-FR/*.parquet"
- config_name: "fa-GA"
data_files:
- split: train
path: "data/fa-GA/*.parquet"
- config_name: "fa-GB"
data_files:
- split: train
path: "data/fa-GB/*.parquet"
- config_name: "fa-GE"
data_files:
- split: train
path: "data/fa-GE/*.parquet"
- config_name: "fa-GQ"
data_files:
- split: train
path: "data/fa-GQ/*.parquet"
- config_name: "fa-HR"
data_files:
- split: train
path: "data/fa-HR/*.parquet"
- config_name: "fa-IM"
data_files:
- split: train
path: "data/fa-IM/*.parquet"
- config_name: "fa-IN"
data_files:
- split: train
path: "data/fa-IN/*.parquet"
- config_name: "fa-IO"
data_files:
- split: train
path: "data/fa-IO/*.parquet"
- config_name: "fa-IR"
data_files:
- split: train
path: "data/fa-IR/*.parquet"
- config_name: "fa-IT"
data_files:
- split: train
path: "data/fa-IT/*.parquet"
- config_name: "fa-JP"
data_files:
- split: train
path: "data/fa-JP/*.parquet"
- config_name: "fa-ME"
data_files:
- split: train
path: "data/fa-ME/*.parquet"
- config_name: "fa-ML"
data_files:
- split: train
path: "data/fa-ML/*.parquet"
- config_name: "fa-NL"
data_files:
- split: train
path: "data/fa-NL/*.parquet"
- config_name: "fa-NO"
data_files:
- split: train
path: "data/fa-NO/*.parquet"
- config_name: "fa-NU"
data_files:
- split: train
path: "data/fa-NU/*.parquet"
- config_name: "fa-PL"
data_files:
- split: train
path: "data/fa-PL/*.parquet"
- config_name: "fa-PW"
data_files:
- split: train
path: "data/fa-PW/*.parquet"
- config_name: "fa-RI"
data_files:
- split: train
path: "data/fa-RI/*.parquet"
- config_name: "fa-RU"
data_files:
- split: train
path: "data/fa-RU/*.parquet"
- config_name: "fa-SA"
data_files:
- split: train
path: "data/fa-SA/*.parquet"
- config_name: "fa-SC"
data_files:
- split: train
path: "data/fa-SC/*.parquet"
- config_name: "fa-SE"
data_files:
- split: train
path: "data/fa-SE/*.parquet"
- config_name: "fa-SH"
data_files:
- split: train
path: "data/fa-SH/*.parquet"
- config_name: "fa-ST"
data_files:
- split: train
path: "data/fa-ST/*.parquet"
- config_name: "fa-SY"
data_files:
- split: train
path: "data/fa-SY/*.parquet"
- config_name: "fa-TC"
data_files:
- split: train
path: "data/fa-TC/*.parquet"
- config_name: "fa-TK"
data_files:
- split: train
path: "data/fa-TK/*.parquet"
- config_name: "fa-TL"
data_files:
- split: train
path: "data/fa-TL/*.parquet"
- config_name: "fa-TO"
data_files:
- split: train
path: "data/fa-TO/*.parquet"
- config_name: "fa-TR"
data_files:
- split: train
path: "data/fa-TR/*.parquet"
- config_name: "fa-TV"
data_files:
- split: train
path: "data/fa-TV/*.parquet"
- config_name: "fa-US"
data_files:
- split: train
path: "data/fa-US/*.parquet"
- config_name: "fa-WS"
data_files:
- split: train
path: "data/fa-WS/*.parquet"
- config_name: "fa-XX"
data_files:
- split: train
path: "data/fa-XX/*.parquet"
- config_name: "fa-YE"
data_files:
- split: train
path: "data/fa-YE/*.parquet"
- config_name: "fa-ZA"
data_files:
- split: train
path: "data/fa-ZA/*.parquet"
- config_name: "fi-AI"
data_files:
- split: train
path: "data/fi-AI/*.parquet"
- config_name: "fi-AL"
data_files:
- split: train
path: "data/fi-AL/*.parquet"
- config_name: "fi-AT"
data_files:
- split: train
path: "data/fi-AT/*.parquet"
- config_name: "fi-AU"
data_files:
- split: train
path: "data/fi-AU/*.parquet"
- config_name: "fi-AX"
data_files:
- split: train
path: "data/fi-AX/*.parquet"
- config_name: "fi-BE"
data_files:
- split: train
path: "data/fi-BE/*.parquet"
- config_name: "fi-BR"
data_files:
- split: train
path: "data/fi-BR/*.parquet"
- config_name: "fi-CA"
data_files:
- split: train
path: "data/fi-CA/*.parquet"
- config_name: "fi-CC"
data_files:
- split: train
path: "data/fi-CC/*.parquet"
- config_name: "fi-CF"
data_files:
- split: train
path: "data/fi-CF/*.parquet"
- config_name: "fi-CH"
data_files:
- split: train
path: "data/fi-CH/*.parquet"
- config_name: "fi-CL"
data_files:
- split: train
path: "data/fi-CL/*.parquet"
- config_name: "fi-CN"
data_files:
- split: train
path: "data/fi-CN/*.parquet"
- config_name: "fi-CO"
data_files:
- split: train
path: "data/fi-CO/*.parquet"
- config_name: "fi-CZ"
data_files:
- split: train
path: "data/fi-CZ/*.parquet"
- config_name: "fi-DE"
data_files:
- split: train
path: "data/fi-DE/*.parquet"
- config_name: "fi-DK"
data_files:
- split: train
path: "data/fi-DK/*.parquet"
- config_name: "fi-EE"
data_files:
- split: train
path: "data/fi-EE/*.parquet"
- config_name: "fi-EN"
data_files:
- split: train
path: "data/fi-EN/*.parquet"
- config_name: "fi-ES"
data_files:
- split: train
path: "data/fi-ES/*.parquet"
- config_name: "fi-EU"
data_files:
- split: train
path: "data/fi-EU/*.parquet"
- config_name: "fi-FI"
data_files:
- split: train
path: "data/fi-FI/*.parquet"
- config_name: "fi-FL"
data_files:
- split: train
path: "data/fi-FL/*.parquet"
- config_name: "fi-FM"
data_files:
- split: train
path: "data/fi-FM/*.parquet"
- config_name: "fi-FR"
data_files:
- split: train
path: "data/fi-FR/*.parquet"
- config_name: "fi-GA"
data_files:
- split: train
path: "data/fi-GA/*.parquet"
- config_name: "fi-GB"
data_files:
- split: train
path: "data/fi-GB/*.parquet"
- config_name: "fi-GL"
data_files:
- split: train
path: "data/fi-GL/*.parquet"
- config_name: "fi-GR"
data_files:
- split: train
path: "data/fi-GR/*.parquet"
- config_name: "fi-HU"
data_files:
- split: train
path: "data/fi-HU/*.parquet"
- config_name: "fi-ID"
data_files:
- split: train
path: "data/fi-ID/*.parquet"
- config_name: "fi-IE"
data_files:
- split: train
path: "data/fi-IE/*.parquet"
- config_name: "fi-IL"
data_files:
- split: train
path: "data/fi-IL/*.parquet"
- config_name: "fi-IN"
data_files:
- split: train
path: "data/fi-IN/*.parquet"
- config_name: "fi-IO"
data_files:
- split: train
path: "data/fi-IO/*.parquet"
- config_name: "fi-IS"
data_files:
- split: train
path: "data/fi-IS/*.parquet"
- config_name: "fi-IT"
data_files:
- split: train
path: "data/fi-IT/*.parquet"
- config_name: "fi-JE"
data_files:
- split: train
path: "data/fi-JE/*.parquet"
- config_name: "fi-KZ"
data_files:
- split: train
path: "data/fi-KZ/*.parquet"
- config_name: "fi-LA"
data_files:
- split: train
path: "data/fi-LA/*.parquet"
- config_name: "fi-LI"
data_files:
- split: train
path: "data/fi-LI/*.parquet"
- config_name: "fi-LT"
data_files:
- split: train
path: "data/fi-LT/*.parquet"
- config_name: "fi-LV"
data_files:
- split: train
path: "data/fi-LV/*.parquet"
- config_name: "fi-ME"
data_files:
- split: train
path: "data/fi-ME/*.parquet"
- config_name: "fi-MU"
data_files:
- split: train
path: "data/fi-MU/*.parquet"
- config_name: "fi-MX"
data_files:
- split: train
path: "data/fi-MX/*.parquet"
- config_name: "fi-NL"
data_files:
- split: train
path: "data/fi-NL/*.parquet"
- config_name: "fi-NO"
data_files:
- split: train
path: "data/fi-NO/*.parquet"
- config_name: "fi-NU"
data_files:
- split: train
path: "data/fi-NU/*.parquet"
- config_name: "fi-NZ"
data_files:
- split: train
path: "data/fi-NZ/*.parquet"
- config_name: "fi-PL"
data_files:
- split: train
path: "data/fi-PL/*.parquet"
- config_name: "fi-PW"
data_files:
- split: train
path: "data/fi-PW/*.parquet"
- config_name: "fi-RO"
data_files:
- split: train
path: "data/fi-RO/*.parquet"
- config_name: "fi-RU"
data_files:
- split: train
path: "data/fi-RU/*.parquet"
- config_name: "fi-SE"
data_files:
- split: train
path: "data/fi-SE/*.parquet"
- config_name: "fi-SH"
data_files:
- split: train
path: "data/fi-SH/*.parquet"
- config_name: "fi-SI"
data_files:
- split: train
path: "data/fi-SI/*.parquet"
- config_name: "fi-SK"
data_files:
- split: train
path: "data/fi-SK/*.parquet"
- config_name: "fi-TK"
data_files:
- split: train
path: "data/fi-TK/*.parquet"
- config_name: "fi-TR"
data_files:
- split: train
path: "data/fi-TR/*.parquet"
- config_name: "fi-TV"
data_files:
- split: train
path: "data/fi-TV/*.parquet"
- config_name: "fi-UA"
data_files:
- split: train
path: "data/fi-UA/*.parquet"
- config_name: "fi-UK"
data_files:
- split: train
path: "data/fi-UK/*.parquet"
- config_name: "fi-US"
data_files:
- split: train
path: "data/fi-US/*.parquet"
- config_name: "fi-VN"
data_files:
- split: train
path: "data/fi-VN/*.parquet"
- config_name: "fi-WS"
data_files:
- split: train
path: "data/fi-WS/*.parquet"
- config_name: "fi-XX"
data_files:
- split: train
path: "data/fi-XX/*.parquet"
- config_name: "fi-ZA"
data_files:
- split: train
path: "data/fi-ZA/*.parquet"
- config_name: "fr-AA"
data_files:
- split: train
path: "data/fr-AA/*.parquet"
- config_name: "fr-AD"
data_files:
- split: train
path: "data/fr-AD/*.parquet"
- config_name: "fr-AE"
data_files:
- split: train
path: "data/fr-AE/*.parquet"
- config_name: "fr-AF"
data_files:
- split: train
path: "data/fr-AF/*.parquet"
- config_name: "fr-AG"
data_files:
- split: train
path: "data/fr-AG/*.parquet"
- config_name: "fr-AI"
data_files:
- split: train
path: "data/fr-AI/*.parquet"
- config_name: "fr-AL"
data_files:
- split: train
path: "data/fr-AL/*.parquet"
- config_name: "fr-AM"
data_files:
- split: train
path: "data/fr-AM/*.parquet"
- config_name: "fr-AO"
data_files:
- split: train
path: "data/fr-AO/*.parquet"
- config_name: "fr-AR"
data_files:
- split: train
path: "data/fr-AR/*.parquet"
- config_name: "fr-AS"
data_files:
- split: train
path: "data/fr-AS/*.parquet"
- config_name: "fr-AT"
data_files:
- split: train
path: "data/fr-AT/*.parquet"
- config_name: "fr-AU"
data_files:
- split: train
path: "data/fr-AU/*.parquet"
- config_name: "fr-AX"
data_files:
- split: train
path: "data/fr-AX/*.parquet"
- config_name: "fr-AZ"
data_files:
- split: train
path: "data/fr-AZ/*.parquet"
- config_name: "fr-BA"
data_files:
- split: train
path: "data/fr-BA/*.parquet"
- config_name: "fr-BD"
data_files:
- split: train
path: "data/fr-BD/*.parquet"
- config_name: "fr-BE"
data_files:
- split: train
path: "data/fr-BE/*.parquet"
- config_name: "fr-BF"
data_files:
- split: train
path: "data/fr-BF/*.parquet"
- config_name: "fr-BG"
data_files:
- split: train
path: "data/fr-BG/*.parquet"
- config_name: "fr-BI"
data_files:
- split: train
path: "data/fr-BI/*.parquet"
- config_name: "fr-BJ"
data_files:
- split: train
path: "data/fr-BJ/*.parquet"
- config_name: "fr-BM"
data_files:
- split: train
path: "data/fr-BM/*.parquet"
- config_name: "fr-BO"
data_files:
- split: train
path: "data/fr-BO/*.parquet"
- config_name: "fr-BR"
data_files:
- split: train
path: "data/fr-BR/*.parquet"
- config_name: "fr-BW"
data_files:
- split: train
path: "data/fr-BW/*.parquet"
- config_name: "fr-BY"
data_files:
- split: train
path: "data/fr-BY/*.parquet"
- config_name: "fr-BZ"
data_files:
- split: train
path: "data/fr-BZ/*.parquet"
- config_name: "fr-CA"
data_files:
- split: train
path: "data/fr-CA/*.parquet"
- config_name: "fr-CC"
data_files:
- split: train
path: "data/fr-CC/*.parquet"
- config_name: "fr-CD"
data_files:
- split: train
path: "data/fr-CD/*.parquet"
- config_name: "fr-CF"
data_files:
- split: train
path: "data/fr-CF/*.parquet"
- config_name: "fr-CG"
data_files:
- split: train
path: "data/fr-CG/*.parquet"
- config_name: "fr-CH"
data_files:
- split: train
path: "data/fr-CH/*.parquet"
- config_name: "fr-CI"
data_files:
- split: train
path: "data/fr-CI/*.parquet"
- config_name: "fr-CL"
data_files:
- split: train
path: "data/fr-CL/*.parquet"
- config_name: "fr-CM"
data_files:
- split: train
path: "data/fr-CM/*.parquet"
- config_name: "fr-CN"
data_files:
- split: train
path: "data/fr-CN/*.parquet"
- config_name: "fr-CO"
data_files:
- split: train
path: "data/fr-CO/*.parquet"
- config_name: "fr-CR"
data_files:
- split: train
path: "data/fr-CR/*.parquet"
- config_name: "fr-CS"
data_files:
- split: train
path: "data/fr-CS/*.parquet"
- config_name: "fr-CU"
data_files:
- split: train
path: "data/fr-CU/*.parquet"
- config_name: "fr-CX"
data_files:
- split: train
path: "data/fr-CX/*.parquet"
- config_name: "fr-CY"
data_files:
- split: train
path: "data/fr-CY/*.parquet"
- config_name: "fr-CZ"
data_files:
- split: train
path: "data/fr-CZ/*.parquet"
- config_name: "fr-DE"
data_files:
- split: train
path: "data/fr-DE/*.parquet"
- config_name: "fr-DJ"
data_files:
- split: train
path: "data/fr-DJ/*.parquet"
- config_name: "fr-DK"
data_files:
- split: train
path: "data/fr-DK/*.parquet"
- config_name: "fr-DO"
data_files:
- split: train
path: "data/fr-DO/*.parquet"
- config_name: "fr-DZ"
data_files:
- split: train
path: "data/fr-DZ/*.parquet"
- config_name: "fr-EC"
data_files:
- split: train
path: "data/fr-EC/*.parquet"
- config_name: "fr-EE"
data_files:
- split: train
path: "data/fr-EE/*.parquet"
- config_name: "fr-EG"
data_files:
- split: train
path: "data/fr-EG/*.parquet"
- config_name: "fr-EN"
data_files:
- split: train
path: "data/fr-EN/*.parquet"
- config_name: "fr-ES"
data_files:
- split: train
path: "data/fr-ES/*.parquet"
- config_name: "fr-EU"
data_files:
- split: train
path: "data/fr-EU/*.parquet"
- config_name: "fr-FI"
data_files:
- split: train
path: "data/fr-FI/*.parquet"
- config_name: "fr-FJ"
data_files:
- split: train
path: "data/fr-FJ/*.parquet"
- config_name: "fr-FM"
data_files:
- split: train
path: "data/fr-FM/*.parquet"
- config_name: "fr-FO"
data_files:
- split: train
path: "data/fr-FO/*.parquet"
- config_name: "fr-FR"
data_files:
- split: train
path: "data/fr-FR/*.parquet"
- config_name: "fr-GA"
data_files:
- split: train
path: "data/fr-GA/*.parquet"
- config_name: "fr-GB"
data_files:
- split: train
path: "data/fr-GB/*.parquet"
- config_name: "fr-GD"
data_files:
- split: train
path: "data/fr-GD/*.parquet"
- config_name: "fr-GE"
data_files:
- split: train
path: "data/fr-GE/*.parquet"
- config_name: "fr-GF"
data_files:
- split: train
path: "data/fr-GF/*.parquet"
- config_name: "fr-GG"
data_files:
- split: train
path: "data/fr-GG/*.parquet"
- config_name: "fr-GN"
data_files:
- split: train
path: "data/fr-GN/*.parquet"
- config_name: "fr-GP"
data_files:
- split: train
path: "data/fr-GP/*.parquet"
- config_name: "fr-GQ"
data_files:
- split: train
path: "data/fr-GQ/*.parquet"
- config_name: "fr-GR"
data_files:
- split: train
path: "data/fr-GR/*.parquet"
- config_name: "fr-GT"
data_files:
- split: train
path: "data/fr-GT/*.parquet"
- config_name: "fr-GX"
data_files:
- split: train
path: "data/fr-GX/*.parquet"
- config_name: "fr-GY"
data_files:
- split: train
path: "data/fr-GY/*.parquet"
- config_name: "fr-HK"
data_files:
- split: train
path: "data/fr-HK/*.parquet"
- config_name: "fr-HR"
data_files:
- split: train
path: "data/fr-HR/*.parquet"
- config_name: "fr-HT"
data_files:
- split: train
path: "data/fr-HT/*.parquet"
- config_name: "fr-HU"
data_files:
- split: train
path: "data/fr-HU/*.parquet"
- config_name: "fr-ID"
data_files:
- split: train
path: "data/fr-ID/*.parquet"
- config_name: "fr-IE"
data_files:
- split: train
path: "data/fr-IE/*.parquet"
- config_name: "fr-IL"
data_files:
- split: train
path: "data/fr-IL/*.parquet"
- config_name: "fr-IM"
data_files:
- split: train
path: "data/fr-IM/*.parquet"
- config_name: "fr-IN"
data_files:
- split: train
path: "data/fr-IN/*.parquet"
- config_name: "fr-IO"
data_files:
- split: train
path: "data/fr-IO/*.parquet"
- config_name: "fr-IR"
data_files:
- split: train
path: "data/fr-IR/*.parquet"
- config_name: "fr-IS"
data_files:
- split: train
path: "data/fr-IS/*.parquet"
- config_name: "fr-IT"
data_files:
- split: train
path: "data/fr-IT/*.parquet"
- config_name: "fr-JO"
data_files:
- split: train
path: "data/fr-JO/*.parquet"
- config_name: "fr-JP"
data_files:
- split: train
path: "data/fr-JP/*.parquet"
- config_name: "fr-KE"
data_files:
- split: train
path: "data/fr-KE/*.parquet"
- config_name: "fr-KG"
data_files:
- split: train
path: "data/fr-KG/*.parquet"
- config_name: "fr-KH"
data_files:
- split: train
path: "data/fr-KH/*.parquet"
- config_name: "fr-KM"
data_files:
- split: train
path: "data/fr-KM/*.parquet"
- config_name: "fr-KP"
data_files:
- split: train
path: "data/fr-KP/*.parquet"
- config_name: "fr-KR"
data_files:
- split: train
path: "data/fr-KR/*.parquet"
- config_name: "fr-KW"
data_files:
- split: train
path: "data/fr-KW/*.parquet"
- config_name: "fr-KZ"
data_files:
- split: train
path: "data/fr-KZ/*.parquet"
- config_name: "fr-LA"
data_files:
- split: train
path: "data/fr-LA/*.parquet"
- config_name: "fr-LB"
data_files:
- split: train
path: "data/fr-LB/*.parquet"
- config_name: "fr-LI"
data_files:
- split: train
path: "data/fr-LI/*.parquet"
- config_name: "fr-LT"
data_files:
- split: train
path: "data/fr-LT/*.parquet"
- config_name: "fr-LU"
data_files:
- split: train
path: "data/fr-LU/*.parquet"
- config_name: "fr-LV"
data_files:
- split: train
path: "data/fr-LV/*.parquet"
- config_name: "fr-LY"
data_files:
- split: train
path: "data/fr-LY/*.parquet"
- config_name: "fr-MA"
data_files:
- split: train
path: "data/fr-MA/*.parquet"
- config_name: "fr-MC"
data_files:
- split: train
path: "data/fr-MC/*.parquet"
- config_name: "fr-MD"
data_files:
- split: train
path: "data/fr-MD/*.parquet"
- config_name: "fr-ME"
data_files:
- split: train
path: "data/fr-ME/*.parquet"
- config_name: "fr-MG"
data_files:
- split: train
path: "data/fr-MG/*.parquet"
- config_name: "fr-MK"
data_files:
- split: train
path: "data/fr-MK/*.parquet"
- config_name: "fr-ML"
data_files:
- split: train
path: "data/fr-ML/*.parquet"
- config_name: "fr-MN"
data_files:
- split: train
path: "data/fr-MN/*.parquet"
- config_name: "fr-MQ"
data_files:
- split: train
path: "data/fr-MQ/*.parquet"
- config_name: "fr-MR"
data_files:
- split: train
path: "data/fr-MR/*.parquet"
- config_name: "fr-MS"
data_files:
- split: train
path: "data/fr-MS/*.parquet"
- config_name: "fr-MT"
data_files:
- split: train
path: "data/fr-MT/*.parquet"
- config_name: "fr-MU"
data_files:
- split: train
path: "data/fr-MU/*.parquet"
- config_name: "fr-MX"
data_files:
- split: train
path: "data/fr-MX/*.parquet"
- config_name: "fr-MY"
data_files:
- split: train
path: "data/fr-MY/*.parquet"
- config_name: "fr-MZ"
data_files:
- split: train
path: "data/fr-MZ/*.parquet"
- config_name: "fr-NC"
data_files:
- split: train
path: "data/fr-NC/*.parquet"
- config_name: "fr-NE"
data_files:
- split: train
path: "data/fr-NE/*.parquet"
- config_name: "fr-NF"
data_files:
- split: train
path: "data/fr-NF/*.parquet"
- config_name: "fr-NG"
data_files:
- split: train
path: "data/fr-NG/*.parquet"
- config_name: "fr-NL"
data_files:
- split: train
path: "data/fr-NL/*.parquet"
- config_name: "fr-NO"
data_files:
- split: train
path: "data/fr-NO/*.parquet"
- config_name: "fr-NU"
data_files:
- split: train
path: "data/fr-NU/*.parquet"
- config_name: "fr-NZ"
data_files:
- split: train
path: "data/fr-NZ/*.parquet"
- config_name: "fr-OC"
data_files:
- split: train
path: "data/fr-OC/*.parquet"
- config_name: "fr-OM"
data_files:
- split: train
path: "data/fr-OM/*.parquet"
- config_name: "fr-PE"
data_files:
- split: train
path: "data/fr-PE/*.parquet"
- config_name: "fr-PF"
data_files:
- split: train
path: "data/fr-PF/*.parquet"
- config_name: "fr-PH"
data_files:
- split: train
path: "data/fr-PH/*.parquet"
- config_name: "fr-PK"
data_files:
- split: train
path: "data/fr-PK/*.parquet"
- config_name: "fr-PL"
data_files:
- split: train
path: "data/fr-PL/*.parquet"
- config_name: "fr-PM"
data_files:
- split: train
path: "data/fr-PM/*.parquet"
- config_name: "fr-PS"
data_files:
- split: train
path: "data/fr-PS/*.parquet"
- config_name: "fr-PT"
data_files:
- split: train
path: "data/fr-PT/*.parquet"
- config_name: "fr-PW"
data_files:
- split: train
path: "data/fr-PW/*.parquet"
- config_name: "fr-QC"
data_files:
- split: train
path: "data/fr-QC/*.parquet"
- config_name: "fr-RE"
data_files:
- split: train
path: "data/fr-RE/*.parquet"
- config_name: "fr-RO"
data_files:
- split: train
path: "data/fr-RO/*.parquet"
- config_name: "fr-RS"
data_files:
- split: train
path: "data/fr-RS/*.parquet"
- config_name: "fr-RT"
data_files:
- split: train
path: "data/fr-RT/*.parquet"
- config_name: "fr-RU"
data_files:
- split: train
path: "data/fr-RU/*.parquet"
- config_name: "fr-RW"
data_files:
- split: train
path: "data/fr-RW/*.parquet"
- config_name: "fr-SA"
data_files:
- split: train
path: "data/fr-SA/*.parquet"
- config_name: "fr-SC"
data_files:
- split: train
path: "data/fr-SC/*.parquet"
- config_name: "fr-SE"
data_files:
- split: train
path: "data/fr-SE/*.parquet"
- config_name: "fr-SG"
data_files:
- split: train
path: "data/fr-SG/*.parquet"
- config_name: "fr-SH"
data_files:
- split: train
path: "data/fr-SH/*.parquet"
- config_name: "fr-SI"
data_files:
- split: train
path: "data/fr-SI/*.parquet"
- config_name: "fr-SK"
data_files:
- split: train
path: "data/fr-SK/*.parquet"
- config_name: "fr-SM"
data_files:
- split: train
path: "data/fr-SM/*.parquet"
- config_name: "fr-SN"
data_files:
- split: train
path: "data/fr-SN/*.parquet"
- config_name: "fr-SO"
data_files:
- split: train
path: "data/fr-SO/*.parquet"
- config_name: "fr-ST"
data_files:
- split: train
path: "data/fr-ST/*.parquet"
- config_name: "fr-SV"
data_files:
- split: train
path: "data/fr-SV/*.parquet"
- config_name: "fr-SX"
data_files:
- split: train
path: "data/fr-SX/*.parquet"
- config_name: "fr-SY"
data_files:
- split: train
path: "data/fr-SY/*.parquet"
- config_name: "fr-TG"
data_files:
- split: train
path: "data/fr-TG/*.parquet"
- config_name: "fr-TH"
data_files:
- split: train
path: "data/fr-TH/*.parquet"
- config_name: "fr-TK"
data_files:
- split: train
path: "data/fr-TK/*.parquet"
- config_name: "fr-TL"
data_files:
- split: train
path: "data/fr-TL/*.parquet"
- config_name: "fr-TN"
data_files:
- split: train
path: "data/fr-TN/*.parquet"
- config_name: "fr-TO"
data_files:
- split: train
path: "data/fr-TO/*.parquet"
- config_name: "fr-TR"
data_files:
- split: train
path: "data/fr-TR/*.parquet"
- config_name: "fr-TT"
data_files:
- split: train
path: "data/fr-TT/*.parquet"
- config_name: "fr-TU"
data_files:
- split: train
path: "data/fr-TU/*.parquet"
- config_name: "fr-TV"
data_files:
- split: train
path: "data/fr-TV/*.parquet"
- config_name: "fr-TW"
data_files:
- split: train
path: "data/fr-TW/*.parquet"
- config_name: "fr-TZ"
data_files:
- split: train
path: "data/fr-TZ/*.parquet"
- config_name: "fr-UA"
data_files:
- split: train
path: "data/fr-UA/*.parquet"
- config_name: "fr-UG"
data_files:
- split: train
path: "data/fr-UG/*.parquet"
- config_name: "fr-UK"
data_files:
- split: train
path: "data/fr-UK/*.parquet"
- config_name: "fr-US"
data_files:
- split: train
path: "data/fr-US/*.parquet"
- config_name: "fr-UY"
data_files:
- split: train
path: "data/fr-UY/*.parquet"
- config_name: "fr-UZ"
data_files:
- split: train
path: "data/fr-UZ/*.parquet"
- config_name: "fr-VA"
data_files:
- split: train
path: "data/fr-VA/*.parquet"
- config_name: "fr-VE"
data_files:
- split: train
path: "data/fr-VE/*.parquet"
- config_name: "fr-VL"
data_files:
- split: train
path: "data/fr-VL/*.parquet"
- config_name: "fr-VN"
data_files:
- split: train
path: "data/fr-VN/*.parquet"
- config_name: "fr-VU"
data_files:
- split: train
path: "data/fr-VU/*.parquet"
- config_name: "fr-WF"
data_files:
- split: train
path: "data/fr-WF/*.parquet"
- config_name: "fr-WS"
data_files:
- split: train
path: "data/fr-WS/*.parquet"
- config_name: "fr-XL"
data_files:
- split: train
path: "data/fr-XL/*.parquet"
- config_name: "fr-XX"
data_files:
- split: train
path: "data/fr-XX/*.parquet"
- config_name: "fr-YT"
data_files:
- split: train
path: "data/fr-YT/*.parquet"
- config_name: "fr-ZA"
data_files:
- split: train
path: "data/fr-ZA/*.parquet"
- config_name: "fr-ZW"
data_files:
- split: train
path: "data/fr-ZW/*.parquet"
- config_name: "fr-ZZ"
data_files:
- split: train
path: "data/fr-ZZ/*.parquet"
- config_name: "fy-BR"
data_files:
- split: train
path: "data/fy-BR/*.parquet"
- config_name: "fy-EU"
data_files:
- split: train
path: "data/fy-EU/*.parquet"
- config_name: "fy-FR"
data_files:
- split: train
path: "data/fy-FR/*.parquet"
- config_name: "fy-IO"
data_files:
- split: train
path: "data/fy-IO/*.parquet"
- config_name: "fy-NL"
data_files:
- split: train
path: "data/fy-NL/*.parquet"
- config_name: "fy-PL"
data_files:
- split: train
path: "data/fy-PL/*.parquet"
- config_name: "fy-US"
data_files:
- split: train
path: "data/fy-US/*.parquet"
- config_name: "fy-XX"
data_files:
- split: train
path: "data/fy-XX/*.parquet"
- config_name: "ga-DE"
data_files:
- split: train
path: "data/ga-DE/*.parquet"
- config_name: "ga-EU"
data_files:
- split: train
path: "data/ga-EU/*.parquet"
- config_name: "ga-GA"
data_files:
- split: train
path: "data/ga-GA/*.parquet"
- config_name: "ga-GB"
data_files:
- split: train
path: "data/ga-GB/*.parquet"
- config_name: "ga-IE"
data_files:
- split: train
path: "data/ga-IE/*.parquet"
- config_name: "ga-PW"
data_files:
- split: train
path: "data/ga-PW/*.parquet"
- config_name: "ga-US"
data_files:
- split: train
path: "data/ga-US/*.parquet"
- config_name: "ga-XX"
data_files:
- split: train
path: "data/ga-XX/*.parquet"
- config_name: "gd-GB"
data_files:
- split: train
path: "data/gd-GB/*.parquet"
- config_name: "gd-XX"
data_files:
- split: train
path: "data/gd-XX/*.parquet"
- config_name: "gl-CO"
data_files:
- split: train
path: "data/gl-CO/*.parquet"
- config_name: "gl-ES"
data_files:
- split: train
path: "data/gl-ES/*.parquet"
- config_name: "gl-EU"
data_files:
- split: train
path: "data/gl-EU/*.parquet"
- config_name: "gl-FR"
data_files:
- split: train
path: "data/gl-FR/*.parquet"
- config_name: "gl-GB"
data_files:
- split: train
path: "data/gl-GB/*.parquet"
- config_name: "gl-GL"
data_files:
- split: train
path: "data/gl-GL/*.parquet"
- config_name: "gl-PT"
data_files:
- split: train
path: "data/gl-PT/*.parquet"
- config_name: "gl-RU"
data_files:
- split: train
path: "data/gl-RU/*.parquet"
- config_name: "gl-TV"
data_files:
- split: train
path: "data/gl-TV/*.parquet"
- config_name: "gl-US"
data_files:
- split: train
path: "data/gl-US/*.parquet"
- config_name: "gl-XX"
data_files:
- split: train
path: "data/gl-XX/*.parquet"
- config_name: "gn-XX"
data_files:
- split: train
path: "data/gn-XX/*.parquet"
- config_name: "gu-GB"
data_files:
- split: train
path: "data/gu-GB/*.parquet"
- config_name: "gu-IN"
data_files:
- split: train
path: "data/gu-IN/*.parquet"
- config_name: "gu-US"
data_files:
- split: train
path: "data/gu-US/*.parquet"
- config_name: "gu-XX"
data_files:
- split: train
path: "data/gu-XX/*.parquet"
- config_name: "he-AE"
data_files:
- split: train
path: "data/he-AE/*.parquet"
- config_name: "he-AL"
data_files:
- split: train
path: "data/he-AL/*.parquet"
- config_name: "he-AR"
data_files:
- split: train
path: "data/he-AR/*.parquet"
- config_name: "he-AU"
data_files:
- split: train
path: "data/he-AU/*.parquet"
- config_name: "he-BE"
data_files:
- split: train
path: "data/he-BE/*.parquet"
- config_name: "he-BR"
data_files:
- split: train
path: "data/he-BR/*.parquet"
- config_name: "he-BZ"
data_files:
- split: train
path: "data/he-BZ/*.parquet"
- config_name: "he-CA"
data_files:
- split: train
path: "data/he-CA/*.parquet"
- config_name: "he-CN"
data_files:
- split: train
path: "data/he-CN/*.parquet"
- config_name: "he-CO"
data_files:
- split: train
path: "data/he-CO/*.parquet"
- config_name: "he-CZ"
data_files:
- split: train
path: "data/he-CZ/*.parquet"
- config_name: "he-DE"
data_files:
- split: train
path: "data/he-DE/*.parquet"
- config_name: "he-DK"
data_files:
- split: train
path: "data/he-DK/*.parquet"
- config_name: "he-EE"
data_files:
- split: train
path: "data/he-EE/*.parquet"
- config_name: "he-EN"
data_files:
- split: train
path: "data/he-EN/*.parquet"
- config_name: "he-ES"
data_files:
- split: train
path: "data/he-ES/*.parquet"
- config_name: "he-EU"
data_files:
- split: train
path: "data/he-EU/*.parquet"
- config_name: "he-FM"
data_files:
- split: train
path: "data/he-FM/*.parquet"
- config_name: "he-FR"
data_files:
- split: train
path: "data/he-FR/*.parquet"
- config_name: "he-GB"
data_files:
- split: train
path: "data/he-GB/*.parquet"
- config_name: "he-GR"
data_files:
- split: train
path: "data/he-GR/*.parquet"
- config_name: "he-HE"
data_files:
- split: train
path: "data/he-HE/*.parquet"
- config_name: "he-HK"
data_files:
- split: train
path: "data/he-HK/*.parquet"
- config_name: "he-IL"
data_files:
- split: train
path: "data/he-IL/*.parquet"
- config_name: "he-IO"
data_files:
- split: train
path: "data/he-IO/*.parquet"
- config_name: "he-IS"
data_files:
- split: train
path: "data/he-IS/*.parquet"
- config_name: "he-IT"
data_files:
- split: train
path: "data/he-IT/*.parquet"
- config_name: "he-IW"
data_files:
- split: train
path: "data/he-IW/*.parquet"
- config_name: "he-JP"
data_files:
- split: train
path: "data/he-JP/*.parquet"
- config_name: "he-LY"
data_files:
- split: train
path: "data/he-LY/*.parquet"
- config_name: "he-ME"
data_files:
- split: train
path: "data/he-ME/*.parquet"
- config_name: "he-MY"
data_files:
- split: train
path: "data/he-MY/*.parquet"
- config_name: "he-PL"
data_files:
- split: train
path: "data/he-PL/*.parquet"
- config_name: "he-PW"
data_files:
- split: train
path: "data/he-PW/*.parquet"
- config_name: "he-RO"
data_files:
- split: train
path: "data/he-RO/*.parquet"
- config_name: "he-RU"
data_files:
- split: train
path: "data/he-RU/*.parquet"
- config_name: "he-SE"
data_files:
- split: train
path: "data/he-SE/*.parquet"
- config_name: "he-SY"
data_files:
- split: train
path: "data/he-SY/*.parquet"
- config_name: "he-TK"
data_files:
- split: train
path: "data/he-TK/*.parquet"
- config_name: "he-TV"
data_files:
- split: train
path: "data/he-TV/*.parquet"
- config_name: "he-UA"
data_files:
- split: train
path: "data/he-UA/*.parquet"
- config_name: "he-US"
data_files:
- split: train
path: "data/he-US/*.parquet"
- config_name: "he-UZ"
data_files:
- split: train
path: "data/he-UZ/*.parquet"
- config_name: "he-WS"
data_files:
- split: train
path: "data/he-WS/*.parquet"
- config_name: "he-XX"
data_files:
- split: train
path: "data/he-XX/*.parquet"
- config_name: "hi-AI"
data_files:
- split: train
path: "data/hi-AI/*.parquet"
- config_name: "hi-CA"
data_files:
- split: train
path: "data/hi-CA/*.parquet"
- config_name: "hi-CN"
data_files:
- split: train
path: "data/hi-CN/*.parquet"
- config_name: "hi-EU"
data_files:
- split: train
path: "data/hi-EU/*.parquet"
- config_name: "hi-GB"
data_files:
- split: train
path: "data/hi-GB/*.parquet"
- config_name: "hi-HI"
data_files:
- split: train
path: "data/hi-HI/*.parquet"
- config_name: "hi-IN"
data_files:
- split: train
path: "data/hi-IN/*.parquet"
- config_name: "hi-IO"
data_files:
- split: train
path: "data/hi-IO/*.parquet"
- config_name: "hi-JA"
data_files:
- split: train
path: "data/hi-JA/*.parquet"
- config_name: "hi-ME"
data_files:
- split: train
path: "data/hi-ME/*.parquet"
- config_name: "hi-ML"
data_files:
- split: train
path: "data/hi-ML/*.parquet"
- config_name: "hi-TV"
data_files:
- split: train
path: "data/hi-TV/*.parquet"
- config_name: "hi-US"
data_files:
- split: train
path: "data/hi-US/*.parquet"
- config_name: "hi-XX"
data_files:
- split: train
path: "data/hi-XX/*.parquet"
- config_name: "hr-BA"
data_files:
- split: train
path: "data/hr-BA/*.parquet"
- config_name: "hr-CA"
data_files:
- split: train
path: "data/hr-CA/*.parquet"
- config_name: "hr-CC"
data_files:
- split: train
path: "data/hr-CC/*.parquet"
- config_name: "hr-CN"
data_files:
- split: train
path: "data/hr-CN/*.parquet"
- config_name: "hr-CZ"
data_files:
- split: train
path: "data/hr-CZ/*.parquet"
- config_name: "hr-DE"
data_files:
- split: train
path: "data/hr-DE/*.parquet"
- config_name: "hr-EU"
data_files:
- split: train
path: "data/hr-EU/*.parquet"
- config_name: "hr-FR"
data_files:
- split: train
path: "data/hr-FR/*.parquet"
- config_name: "hr-GB"
data_files:
- split: train
path: "data/hr-GB/*.parquet"
- config_name: "hr-HR"
data_files:
- split: train
path: "data/hr-HR/*.parquet"
- config_name: "hr-HU"
data_files:
- split: train
path: "data/hr-HU/*.parquet"
- config_name: "hr-IE"
data_files:
- split: train
path: "data/hr-IE/*.parquet"
- config_name: "hr-IN"
data_files:
- split: train
path: "data/hr-IN/*.parquet"
- config_name: "hr-IO"
data_files:
- split: train
path: "data/hr-IO/*.parquet"
- config_name: "hr-IT"
data_files:
- split: train
path: "data/hr-IT/*.parquet"
- config_name: "hr-ME"
data_files:
- split: train
path: "data/hr-ME/*.parquet"
- config_name: "hr-PL"
data_files:
- split: train
path: "data/hr-PL/*.parquet"
- config_name: "hr-PT"
data_files:
- split: train
path: "data/hr-PT/*.parquet"
- config_name: "hr-RS"
data_files:
- split: train
path: "data/hr-RS/*.parquet"
- config_name: "hr-RU"
data_files:
- split: train
path: "data/hr-RU/*.parquet"
- config_name: "hr-SI"
data_files:
- split: train
path: "data/hr-SI/*.parquet"
- config_name: "hr-TV"
data_files:
- split: train
path: "data/hr-TV/*.parquet"
- config_name: "hr-US"
data_files:
- split: train
path: "data/hr-US/*.parquet"
- config_name: "hr-VA"
data_files:
- split: train
path: "data/hr-VA/*.parquet"
- config_name: "hr-WS"
data_files:
- split: train
path: "data/hr-WS/*.parquet"
- config_name: "hr-XX"
data_files:
- split: train
path: "data/hr-XX/*.parquet"
- config_name: "hsb-DE"
data_files:
- split: train
path: "data/hsb-DE/*.parquet"
- config_name: "hsb-HS"
data_files:
- split: train
path: "data/hsb-HS/*.parquet"
- config_name: "hsb-SB"
data_files:
- split: train
path: "data/hsb-SB/*.parquet"
- config_name: "hsb-US"
data_files:
- split: train
path: "data/hsb-US/*.parquet"
- config_name: "hsb-XX"
data_files:
- split: train
path: "data/hsb-XX/*.parquet"
- config_name: "hu-AI"
data_files:
- split: train
path: "data/hu-AI/*.parquet"
- config_name: "hu-AM"
data_files:
- split: train
path: "data/hu-AM/*.parquet"
- config_name: "hu-AR"
data_files:
- split: train
path: "data/hu-AR/*.parquet"
- config_name: "hu-AT"
data_files:
- split: train
path: "data/hu-AT/*.parquet"
- config_name: "hu-AU"
data_files:
- split: train
path: "data/hu-AU/*.parquet"
- config_name: "hu-BE"
data_files:
- split: train
path: "data/hu-BE/*.parquet"
- config_name: "hu-BG"
data_files:
- split: train
path: "data/hu-BG/*.parquet"
- config_name: "hu-BM"
data_files:
- split: train
path: "data/hu-BM/*.parquet"
- config_name: "hu-BR"
data_files:
- split: train
path: "data/hu-BR/*.parquet"
- config_name: "hu-CA"
data_files:
- split: train
path: "data/hu-CA/*.parquet"
- config_name: "hu-CC"
data_files:
- split: train
path: "data/hu-CC/*.parquet"
- config_name: "hu-CF"
data_files:
- split: train
path: "data/hu-CF/*.parquet"
- config_name: "hu-CH"
data_files:
- split: train
path: "data/hu-CH/*.parquet"
- config_name: "hu-CN"
data_files:
- split: train
path: "data/hu-CN/*.parquet"
- config_name: "hu-CO"
data_files:
- split: train
path: "data/hu-CO/*.parquet"
- config_name: "hu-CZ"
data_files:
- split: train
path: "data/hu-CZ/*.parquet"
- config_name: "hu-DE"
data_files:
- split: train
path: "data/hu-DE/*.parquet"
- config_name: "hu-DK"
data_files:
- split: train
path: "data/hu-DK/*.parquet"
- config_name: "hu-EE"
data_files:
- split: train
path: "data/hu-EE/*.parquet"
- config_name: "hu-EN"
data_files:
- split: train
path: "data/hu-EN/*.parquet"
- config_name: "hu-ES"
data_files:
- split: train
path: "data/hu-ES/*.parquet"
- config_name: "hu-EU"
data_files:
- split: train
path: "data/hu-EU/*.parquet"
- config_name: "hu-FI"
data_files:
- split: train
path: "data/hu-FI/*.parquet"
- config_name: "hu-FM"
data_files:
- split: train
path: "data/hu-FM/*.parquet"
- config_name: "hu-FR"
data_files:
- split: train
path: "data/hu-FR/*.parquet"
- config_name: "hu-GA"
data_files:
- split: train
path: "data/hu-GA/*.parquet"
- config_name: "hu-GB"
data_files:
- split: train
path: "data/hu-GB/*.parquet"
- config_name: "hu-GL"
data_files:
- split: train
path: "data/hu-GL/*.parquet"
- config_name: "hu-GQ"
data_files:
- split: train
path: "data/hu-GQ/*.parquet"
- config_name: "hu-GR"
data_files:
- split: train
path: "data/hu-GR/*.parquet"
- config_name: "hu-HR"
data_files:
- split: train
path: "data/hu-HR/*.parquet"
- config_name: "hu-HU"
data_files:
- split: train
path: "data/hu-HU/*.parquet"
- config_name: "hu-ID"
data_files:
- split: train
path: "data/hu-ID/*.parquet"
- config_name: "hu-IE"
data_files:
- split: train
path: "data/hu-IE/*.parquet"
- config_name: "hu-IN"
data_files:
- split: train
path: "data/hu-IN/*.parquet"
- config_name: "hu-IO"
data_files:
- split: train
path: "data/hu-IO/*.parquet"
- config_name: "hu-IT"
data_files:
- split: train
path: "data/hu-IT/*.parquet"
- config_name: "hu-JP"
data_files:
- split: train
path: "data/hu-JP/*.parquet"
- config_name: "hu-KR"
data_files:
- split: train
path: "data/hu-KR/*.parquet"
- config_name: "hu-LA"
data_files:
- split: train
path: "data/hu-LA/*.parquet"
- config_name: "hu-LT"
data_files:
- split: train
path: "data/hu-LT/*.parquet"
- config_name: "hu-LU"
data_files:
- split: train
path: "data/hu-LU/*.parquet"
- config_name: "hu-MA"
data_files:
- split: train
path: "data/hu-MA/*.parquet"
- config_name: "hu-ME"
data_files:
- split: train
path: "data/hu-ME/*.parquet"
- config_name: "hu-ML"
data_files:
- split: train
path: "data/hu-ML/*.parquet"
- config_name: "hu-NL"
data_files:
- split: train
path: "data/hu-NL/*.parquet"
- config_name: "hu-PL"
data_files:
- split: train
path: "data/hu-PL/*.parquet"
- config_name: "hu-PT"
data_files:
- split: train
path: "data/hu-PT/*.parquet"
- config_name: "hu-PW"
data_files:
- split: train
path: "data/hu-PW/*.parquet"
- config_name: "hu-QA"
data_files:
- split: train
path: "data/hu-QA/*.parquet"
- config_name: "hu-RO"
data_files:
- split: train
path: "data/hu-RO/*.parquet"
- config_name: "hu-RS"
data_files:
- split: train
path: "data/hu-RS/*.parquet"
- config_name: "hu-RU"
data_files:
- split: train
path: "data/hu-RU/*.parquet"
- config_name: "hu-SE"
data_files:
- split: train
path: "data/hu-SE/*.parquet"
- config_name: "hu-SI"
data_files:
- split: train
path: "data/hu-SI/*.parquet"
- config_name: "hu-SK"
data_files:
- split: train
path: "data/hu-SK/*.parquet"
- config_name: "hu-TK"
data_files:
- split: train
path: "data/hu-TK/*.parquet"
- config_name: "hu-TO"
data_files:
- split: train
path: "data/hu-TO/*.parquet"
- config_name: "hu-TR"
data_files:
- split: train
path: "data/hu-TR/*.parquet"
- config_name: "hu-TV"
data_files:
- split: train
path: "data/hu-TV/*.parquet"
- config_name: "hu-UA"
data_files:
- split: train
path: "data/hu-UA/*.parquet"
- config_name: "hu-US"
data_files:
- split: train
path: "data/hu-US/*.parquet"
- config_name: "hu-VA"
data_files:
- split: train
path: "data/hu-VA/*.parquet"
- config_name: "hu-VN"
data_files:
- split: train
path: "data/hu-VN/*.parquet"
- config_name: "hu-WS"
data_files:
- split: train
path: "data/hu-WS/*.parquet"
- config_name: "hu-XX"
data_files:
- split: train
path: "data/hu-XX/*.parquet"
- config_name: "hu-YU"
data_files:
- split: train
path: "data/hu-YU/*.parquet"
- config_name: "hu-ZA"
data_files:
- split: train
path: "data/hu-ZA/*.parquet"
- config_name: "hu-ZM"
data_files:
- split: train
path: "data/hu-ZM/*.parquet"
- config_name: "hy-AM"
data_files:
- split: train
path: "data/hy-AM/*.parquet"
- config_name: "hy-AR"
data_files:
- split: train
path: "data/hy-AR/*.parquet"
- config_name: "hy-AU"
data_files:
- split: train
path: "data/hy-AU/*.parquet"
- config_name: "hy-AZ"
data_files:
- split: train
path: "data/hy-AZ/*.parquet"
- config_name: "hy-CA"
data_files:
- split: train
path: "data/hy-CA/*.parquet"
- config_name: "hy-CH"
data_files:
- split: train
path: "data/hy-CH/*.parquet"
- config_name: "hy-CO"
data_files:
- split: train
path: "data/hy-CO/*.parquet"
- config_name: "hy-DE"
data_files:
- split: train
path: "data/hy-DE/*.parquet"
- config_name: "hy-EN"
data_files:
- split: train
path: "data/hy-EN/*.parquet"
- config_name: "hy-ET"
data_files:
- split: train
path: "data/hy-ET/*.parquet"
- config_name: "hy-EU"
data_files:
- split: train
path: "data/hy-EU/*.parquet"
- config_name: "hy-FM"
data_files:
- split: train
path: "data/hy-FM/*.parquet"
- config_name: "hy-FR"
data_files:
- split: train
path: "data/hy-FR/*.parquet"
- config_name: "hy-GB"
data_files:
- split: train
path: "data/hy-GB/*.parquet"
- config_name: "hy-GE"
data_files:
- split: train
path: "data/hy-GE/*.parquet"
- config_name: "hy-GR"
data_files:
- split: train
path: "data/hy-GR/*.parquet"
- config_name: "hy-HU"
data_files:
- split: train
path: "data/hy-HU/*.parquet"
- config_name: "hy-HY"
data_files:
- split: train
path: "data/hy-HY/*.parquet"
- config_name: "hy-IM"
data_files:
- split: train
path: "data/hy-IM/*.parquet"
- config_name: "hy-IR"
data_files:
- split: train
path: "data/hy-IR/*.parquet"
- config_name: "hy-IT"
data_files:
- split: train
path: "data/hy-IT/*.parquet"
- config_name: "hy-LB"
data_files:
- split: train
path: "data/hy-LB/*.parquet"
- config_name: "hy-ME"
data_files:
- split: train
path: "data/hy-ME/*.parquet"
- config_name: "hy-NL"
data_files:
- split: train
path: "data/hy-NL/*.parquet"
- config_name: "hy-PT"
data_files:
- split: train
path: "data/hy-PT/*.parquet"
- config_name: "hy-QA"
data_files:
- split: train
path: "data/hy-QA/*.parquet"
- config_name: "hy-RU"
data_files:
- split: train
path: "data/hy-RU/*.parquet"
- config_name: "hy-TR"
data_files:
- split: train
path: "data/hy-TR/*.parquet"
- config_name: "hy-TV"
data_files:
- split: train
path: "data/hy-TV/*.parquet"
- config_name: "hy-UA"
data_files:
- split: train
path: "data/hy-UA/*.parquet"
- config_name: "hy-US"
data_files:
- split: train
path: "data/hy-US/*.parquet"
- config_name: "hy-XX"
data_files:
- split: train
path: "data/hy-XX/*.parquet"
- config_name: "ia-IT"
data_files:
- split: train
path: "data/ia-IT/*.parquet"
- config_name: "ia-XX"
data_files:
- split: train
path: "data/ia-XX/*.parquet"
- config_name: "id-AA"
data_files:
- split: train
path: "data/id-AA/*.parquet"
- config_name: "id-AE"
data_files:
- split: train
path: "data/id-AE/*.parquet"
- config_name: "id-AI"
data_files:
- split: train
path: "data/id-AI/*.parquet"
- config_name: "id-AM"
data_files:
- split: train
path: "data/id-AM/*.parquet"
- config_name: "id-AR"
data_files:
- split: train
path: "data/id-AR/*.parquet"
- config_name: "id-AT"
data_files:
- split: train
path: "data/id-AT/*.parquet"
- config_name: "id-AU"
data_files:
- split: train
path: "data/id-AU/*.parquet"
- config_name: "id-BA"
data_files:
- split: train
path: "data/id-BA/*.parquet"
- config_name: "id-BE"
data_files:
- split: train
path: "data/id-BE/*.parquet"
- config_name: "id-BN"
data_files:
- split: train
path: "data/id-BN/*.parquet"
- config_name: "id-BO"
data_files:
- split: train
path: "data/id-BO/*.parquet"
- config_name: "id-BR"
data_files:
- split: train
path: "data/id-BR/*.parquet"
- config_name: "id-BZ"
data_files:
- split: train
path: "data/id-BZ/*.parquet"
- config_name: "id-CA"
data_files:
- split: train
path: "data/id-CA/*.parquet"
- config_name: "id-CC"
data_files:
- split: train
path: "data/id-CC/*.parquet"
- config_name: "id-CF"
data_files:
- split: train
path: "data/id-CF/*.parquet"
- config_name: "id-CH"
data_files:
- split: train
path: "data/id-CH/*.parquet"
- config_name: "id-CL"
data_files:
- split: train
path: "data/id-CL/*.parquet"
- config_name: "id-CM"
data_files:
- split: train
path: "data/id-CM/*.parquet"
- config_name: "id-CN"
data_files:
- split: train
path: "data/id-CN/*.parquet"
- config_name: "id-CO"
data_files:
- split: train
path: "data/id-CO/*.parquet"
- config_name: "id-CZ"
data_files:
- split: train
path: "data/id-CZ/*.parquet"
- config_name: "id-DE"
data_files:
- split: train
path: "data/id-DE/*.parquet"
- config_name: "id-DK"
data_files:
- split: train
path: "data/id-DK/*.parquet"
- config_name: "id-DO"
data_files:
- split: train
path: "data/id-DO/*.parquet"
- config_name: "id-EN"
data_files:
- split: train
path: "data/id-EN/*.parquet"
- config_name: "id-ES"
data_files:
- split: train
path: "data/id-ES/*.parquet"
- config_name: "id-EU"
data_files:
- split: train
path: "data/id-EU/*.parquet"
- config_name: "id-FI"
data_files:
- split: train
path: "data/id-FI/*.parquet"
- config_name: "id-FM"
data_files:
- split: train
path: "data/id-FM/*.parquet"
- config_name: "id-FR"
data_files:
- split: train
path: "data/id-FR/*.parquet"
- config_name: "id-GA"
data_files:
- split: train
path: "data/id-GA/*.parquet"
- config_name: "id-GB"
data_files:
- split: train
path: "data/id-GB/*.parquet"
- config_name: "id-GE"
data_files:
- split: train
path: "data/id-GE/*.parquet"
- config_name: "id-GG"
data_files:
- split: train
path: "data/id-GG/*.parquet"
- config_name: "id-GQ"
data_files:
- split: train
path: "data/id-GQ/*.parquet"
- config_name: "id-GT"
data_files:
- split: train
path: "data/id-GT/*.parquet"
- config_name: "id-HR"
data_files:
- split: train
path: "data/id-HR/*.parquet"
- config_name: "id-HU"
data_files:
- split: train
path: "data/id-HU/*.parquet"
- config_name: "id-ID"
data_files:
- split: train
path: "data/id-ID/*.parquet"
- config_name: "id-IE"
data_files:
- split: train
path: "data/id-IE/*.parquet"
- config_name: "id-IN"
data_files:
- split: train
path: "data/id-IN/*.parquet"
- config_name: "id-IO"
data_files:
- split: train
path: "data/id-IO/*.parquet"
- config_name: "id-IR"
data_files:
- split: train
path: "data/id-IR/*.parquet"
- config_name: "id-IS"
data_files:
- split: train
path: "data/id-IS/*.parquet"
- config_name: "id-IT"
data_files:
- split: train
path: "data/id-IT/*.parquet"
- config_name: "id-JP"
data_files:
- split: train
path: "data/id-JP/*.parquet"
- config_name: "id-KE"
data_files:
- split: train
path: "data/id-KE/*.parquet"
- config_name: "id-KR"
data_files:
- split: train
path: "data/id-KR/*.parquet"
- config_name: "id-LA"
data_files:
- split: train
path: "data/id-LA/*.parquet"
- config_name: "id-LC"
data_files:
- split: train
path: "data/id-LC/*.parquet"
- config_name: "id-LI"
data_files:
- split: train
path: "data/id-LI/*.parquet"
- config_name: "id-LK"
data_files:
- split: train
path: "data/id-LK/*.parquet"
- config_name: "id-LT"
data_files:
- split: train
path: "data/id-LT/*.parquet"
- config_name: "id-LV"
data_files:
- split: train
path: "data/id-LV/*.parquet"
- config_name: "id-LY"
data_files:
- split: train
path: "data/id-LY/*.parquet"
- config_name: "id-MA"
data_files:
- split: train
path: "data/id-MA/*.parquet"
- config_name: "id-ME"
data_files:
- split: train
path: "data/id-ME/*.parquet"
- config_name: "id-ML"
data_files:
- split: train
path: "data/id-ML/*.parquet"
- config_name: "id-MO"
data_files:
- split: train
path: "data/id-MO/*.parquet"
- config_name: "id-MS"
data_files:
- split: train
path: "data/id-MS/*.parquet"
- config_name: "id-MX"
data_files:
- split: train
path: "data/id-MX/*.parquet"
- config_name: "id-MY"
data_files:
- split: train
path: "data/id-MY/*.parquet"
- config_name: "id-NG"
data_files:
- split: train
path: "data/id-NG/*.parquet"
- config_name: "id-NL"
data_files:
- split: train
path: "data/id-NL/*.parquet"
- config_name: "id-NO"
data_files:
- split: train
path: "data/id-NO/*.parquet"
- config_name: "id-NU"
data_files:
- split: train
path: "data/id-NU/*.parquet"
- config_name: "id-NZ"
data_files:
- split: train
path: "data/id-NZ/*.parquet"
- config_name: "id-PE"
data_files:
- split: train
path: "data/id-PE/*.parquet"
- config_name: "id-PK"
data_files:
- split: train
path: "data/id-PK/*.parquet"
- config_name: "id-PL"
data_files:
- split: train
path: "data/id-PL/*.parquet"
- config_name: "id-PS"
data_files:
- split: train
path: "data/id-PS/*.parquet"
- config_name: "id-PT"
data_files:
- split: train
path: "data/id-PT/*.parquet"
- config_name: "id-PW"
data_files:
- split: train
path: "data/id-PW/*.parquet"
- config_name: "id-RO"
data_files:
- split: train
path: "data/id-RO/*.parquet"
- config_name: "id-RS"
data_files:
- split: train
path: "data/id-RS/*.parquet"
- config_name: "id-RU"
data_files:
- split: train
path: "data/id-RU/*.parquet"
- config_name: "id-SA"
data_files:
- split: train
path: "data/id-SA/*.parquet"
- config_name: "id-SB"
data_files:
- split: train
path: "data/id-SB/*.parquet"
- config_name: "id-SE"
data_files:
- split: train
path: "data/id-SE/*.parquet"
- config_name: "id-SG"
data_files:
- split: train
path: "data/id-SG/*.parquet"
- config_name: "id-SH"
data_files:
- split: train
path: "data/id-SH/*.parquet"
- config_name: "id-SI"
data_files:
- split: train
path: "data/id-SI/*.parquet"
- config_name: "id-SK"
data_files:
- split: train
path: "data/id-SK/*.parquet"
- config_name: "id-SO"
data_files:
- split: train
path: "data/id-SO/*.parquet"
- config_name: "id-TH"
data_files:
- split: train
path: "data/id-TH/*.parquet"
- config_name: "id-TK"
data_files:
- split: train
path: "data/id-TK/*.parquet"
- config_name: "id-TL"
data_files:
- split: train
path: "data/id-TL/*.parquet"
- config_name: "id-TO"
data_files:
- split: train
path: "data/id-TO/*.parquet"
- config_name: "id-TR"
data_files:
- split: train
path: "data/id-TR/*.parquet"
- config_name: "id-TV"
data_files:
- split: train
path: "data/id-TV/*.parquet"
- config_name: "id-TW"
data_files:
- split: train
path: "data/id-TW/*.parquet"
- config_name: "id-UA"
data_files:
- split: train
path: "data/id-UA/*.parquet"
- config_name: "id-UN"
data_files:
- split: train
path: "data/id-UN/*.parquet"
- config_name: "id-US"
data_files:
- split: train
path: "data/id-US/*.parquet"
- config_name: "id-VN"
data_files:
- split: train
path: "data/id-VN/*.parquet"
- config_name: "id-VU"
data_files:
- split: train
path: "data/id-VU/*.parquet"
- config_name: "id-WS"
data_files:
- split: train
path: "data/id-WS/*.parquet"
- config_name: "id-XX"
data_files:
- split: train
path: "data/id-XX/*.parquet"
- config_name: "id-ZA"
data_files:
- split: train
path: "data/id-ZA/*.parquet"
- config_name: "ilo-US"
data_files:
- split: train
path: "data/ilo-US/*.parquet"
- config_name: "ilo-XX"
data_files:
- split: train
path: "data/ilo-XX/*.parquet"
- config_name: "io-XX"
data_files:
- split: train
path: "data/io-XX/*.parquet"
- config_name: "is-AI"
data_files:
- split: train
path: "data/is-AI/*.parquet"
- config_name: "is-CC"
data_files:
- split: train
path: "data/is-CC/*.parquet"
- config_name: "is-CH"
data_files:
- split: train
path: "data/is-CH/*.parquet"
- config_name: "is-CO"
data_files:
- split: train
path: "data/is-CO/*.parquet"
- config_name: "is-DK"
data_files:
- split: train
path: "data/is-DK/*.parquet"
- config_name: "is-EN"
data_files:
- split: train
path: "data/is-EN/*.parquet"
- config_name: "is-ES"
data_files:
- split: train
path: "data/is-ES/*.parquet"
- config_name: "is-EU"
data_files:
- split: train
path: "data/is-EU/*.parquet"
- config_name: "is-FI"
data_files:
- split: train
path: "data/is-FI/*.parquet"
- config_name: "is-FO"
data_files:
- split: train
path: "data/is-FO/*.parquet"
- config_name: "is-GB"
data_files:
- split: train
path: "data/is-GB/*.parquet"
- config_name: "is-IO"
data_files:
- split: train
path: "data/is-IO/*.parquet"
- config_name: "is-IS"
data_files:
- split: train
path: "data/is-IS/*.parquet"
- config_name: "is-NO"
data_files:
- split: train
path: "data/is-NO/*.parquet"
- config_name: "is-RU"
data_files:
- split: train
path: "data/is-RU/*.parquet"
- config_name: "is-SE"
data_files:
- split: train
path: "data/is-SE/*.parquet"
- config_name: "is-TK"
data_files:
- split: train
path: "data/is-TK/*.parquet"
- config_name: "is-TW"
data_files:
- split: train
path: "data/is-TW/*.parquet"
- config_name: "is-UA"
data_files:
- split: train
path: "data/is-UA/*.parquet"
- config_name: "is-US"
data_files:
- split: train
path: "data/is-US/*.parquet"
- config_name: "is-XX"
data_files:
- split: train
path: "data/is-XX/*.parquet"
- config_name: "it-AA"
data_files:
- split: train
path: "data/it-AA/*.parquet"
- config_name: "it-AD"
data_files:
- split: train
path: "data/it-AD/*.parquet"
- config_name: "it-AE"
data_files:
- split: train
path: "data/it-AE/*.parquet"
- config_name: "it-AI"
data_files:
- split: train
path: "data/it-AI/*.parquet"
- config_name: "it-AL"
data_files:
- split: train
path: "data/it-AL/*.parquet"
- config_name: "it-AM"
data_files:
- split: train
path: "data/it-AM/*.parquet"
- config_name: "it-AR"
data_files:
- split: train
path: "data/it-AR/*.parquet"
- config_name: "it-AS"
data_files:
- split: train
path: "data/it-AS/*.parquet"
- config_name: "it-AT"
data_files:
- split: train
path: "data/it-AT/*.parquet"
- config_name: "it-AU"
data_files:
- split: train
path: "data/it-AU/*.parquet"
- config_name: "it-AX"
data_files:
- split: train
path: "data/it-AX/*.parquet"
- config_name: "it-AZ"
data_files:
- split: train
path: "data/it-AZ/*.parquet"
- config_name: "it-BD"
data_files:
- split: train
path: "data/it-BD/*.parquet"
- config_name: "it-BE"
data_files:
- split: train
path: "data/it-BE/*.parquet"
- config_name: "it-BG"
data_files:
- split: train
path: "data/it-BG/*.parquet"
- config_name: "it-BM"
data_files:
- split: train
path: "data/it-BM/*.parquet"
- config_name: "it-BQ"
data_files:
- split: train
path: "data/it-BQ/*.parquet"
- config_name: "it-BR"
data_files:
- split: train
path: "data/it-BR/*.parquet"
- config_name: "it-BY"
data_files:
- split: train
path: "data/it-BY/*.parquet"
- config_name: "it-BZ"
data_files:
- split: train
path: "data/it-BZ/*.parquet"
- config_name: "it-CA"
data_files:
- split: train
path: "data/it-CA/*.parquet"
- config_name: "it-CC"
data_files:
- split: train
path: "data/it-CC/*.parquet"
- config_name: "it-CD"
data_files:
- split: train
path: "data/it-CD/*.parquet"
- config_name: "it-CF"
data_files:
- split: train
path: "data/it-CF/*.parquet"
- config_name: "it-CH"
data_files:
- split: train
path: "data/it-CH/*.parquet"
- config_name: "it-CI"
data_files:
- split: train
path: "data/it-CI/*.parquet"
- config_name: "it-CL"
data_files:
- split: train
path: "data/it-CL/*.parquet"
- config_name: "it-CN"
data_files:
- split: train
path: "data/it-CN/*.parquet"
- config_name: "it-CO"
data_files:
- split: train
path: "data/it-CO/*.parquet"
- config_name: "it-CR"
data_files:
- split: train
path: "data/it-CR/*.parquet"
- config_name: "it-CU"
data_files:
- split: train
path: "data/it-CU/*.parquet"
- config_name: "it-CX"
data_files:
- split: train
path: "data/it-CX/*.parquet"
- config_name: "it-CY"
data_files:
- split: train
path: "data/it-CY/*.parquet"
- config_name: "it-CZ"
data_files:
- split: train
path: "data/it-CZ/*.parquet"
- config_name: "it-DE"
data_files:
- split: train
path: "data/it-DE/*.parquet"
- config_name: "it-DJ"
data_files:
- split: train
path: "data/it-DJ/*.parquet"
- config_name: "it-DK"
data_files:
- split: train
path: "data/it-DK/*.parquet"
- config_name: "it-DO"
data_files:
- split: train
path: "data/it-DO/*.parquet"
- config_name: "it-EC"
data_files:
- split: train
path: "data/it-EC/*.parquet"
- config_name: "it-EE"
data_files:
- split: train
path: "data/it-EE/*.parquet"
- config_name: "it-EN"
data_files:
- split: train
path: "data/it-EN/*.parquet"
- config_name: "it-ES"
data_files:
- split: train
path: "data/it-ES/*.parquet"
- config_name: "it-ET"
data_files:
- split: train
path: "data/it-ET/*.parquet"
- config_name: "it-EU"
data_files:
- split: train
path: "data/it-EU/*.parquet"
- config_name: "it-FI"
data_files:
- split: train
path: "data/it-FI/*.parquet"
- config_name: "it-FM"
data_files:
- split: train
path: "data/it-FM/*.parquet"
- config_name: "it-FR"
data_files:
- split: train
path: "data/it-FR/*.parquet"
- config_name: "it-GA"
data_files:
- split: train
path: "data/it-GA/*.parquet"
- config_name: "it-GB"
data_files:
- split: train
path: "data/it-GB/*.parquet"
- config_name: "it-GE"
data_files:
- split: train
path: "data/it-GE/*.parquet"
- config_name: "it-GG"
data_files:
- split: train
path: "data/it-GG/*.parquet"
- config_name: "it-GQ"
data_files:
- split: train
path: "data/it-GQ/*.parquet"
- config_name: "it-GR"
data_files:
- split: train
path: "data/it-GR/*.parquet"
- config_name: "it-GT"
data_files:
- split: train
path: "data/it-GT/*.parquet"
- config_name: "it-HR"
data_files:
- split: train
path: "data/it-HR/*.parquet"
- config_name: "it-HU"
data_files:
- split: train
path: "data/it-HU/*.parquet"
- config_name: "it-ID"
data_files:
- split: train
path: "data/it-ID/*.parquet"
- config_name: "it-IE"
data_files:
- split: train
path: "data/it-IE/*.parquet"
- config_name: "it-IL"
data_files:
- split: train
path: "data/it-IL/*.parquet"
- config_name: "it-IM"
data_files:
- split: train
path: "data/it-IM/*.parquet"
- config_name: "it-IN"
data_files:
- split: train
path: "data/it-IN/*.parquet"
- config_name: "it-IO"
data_files:
- split: train
path: "data/it-IO/*.parquet"
- config_name: "it-IR"
data_files:
- split: train
path: "data/it-IR/*.parquet"
- config_name: "it-IS"
data_files:
- split: train
path: "data/it-IS/*.parquet"
- config_name: "it-IT"
data_files:
- split: train
path: "data/it-IT/*.parquet"
- config_name: "it-JA"
data_files:
- split: train
path: "data/it-JA/*.parquet"
- config_name: "it-JP"
data_files:
- split: train
path: "data/it-JP/*.parquet"
- config_name: "it-KE"
data_files:
- split: train
path: "data/it-KE/*.parquet"
- config_name: "it-KR"
data_files:
- split: train
path: "data/it-KR/*.parquet"
- config_name: "it-KZ"
data_files:
- split: train
path: "data/it-KZ/*.parquet"
- config_name: "it-LA"
data_files:
- split: train
path: "data/it-LA/*.parquet"
- config_name: "it-LI"
data_files:
- split: train
path: "data/it-LI/*.parquet"
- config_name: "it-LK"
data_files:
- split: train
path: "data/it-LK/*.parquet"
- config_name: "it-LT"
data_files:
- split: train
path: "data/it-LT/*.parquet"
- config_name: "it-LU"
data_files:
- split: train
path: "data/it-LU/*.parquet"
- config_name: "it-LV"
data_files:
- split: train
path: "data/it-LV/*.parquet"
- config_name: "it-LY"
data_files:
- split: train
path: "data/it-LY/*.parquet"
- config_name: "it-MA"
data_files:
- split: train
path: "data/it-MA/*.parquet"
- config_name: "it-MC"
data_files:
- split: train
path: "data/it-MC/*.parquet"
- config_name: "it-MD"
data_files:
- split: train
path: "data/it-MD/*.parquet"
- config_name: "it-ME"
data_files:
- split: train
path: "data/it-ME/*.parquet"
- config_name: "it-MK"
data_files:
- split: train
path: "data/it-MK/*.parquet"
- config_name: "it-ML"
data_files:
- split: train
path: "data/it-ML/*.parquet"
- config_name: "it-MT"
data_files:
- split: train
path: "data/it-MT/*.parquet"
- config_name: "it-MV"
data_files:
- split: train
path: "data/it-MV/*.parquet"
- config_name: "it-MX"
data_files:
- split: train
path: "data/it-MX/*.parquet"
- config_name: "it-NG"
data_files:
- split: train
path: "data/it-NG/*.parquet"
- config_name: "it-NL"
data_files:
- split: train
path: "data/it-NL/*.parquet"
- config_name: "it-NO"
data_files:
- split: train
path: "data/it-NO/*.parquet"
- config_name: "it-NP"
data_files:
- split: train
path: "data/it-NP/*.parquet"
- config_name: "it-NU"
data_files:
- split: train
path: "data/it-NU/*.parquet"
- config_name: "it-NZ"
data_files:
- split: train
path: "data/it-NZ/*.parquet"
- config_name: "it-PE"
data_files:
- split: train
path: "data/it-PE/*.parquet"
- config_name: "it-PH"
data_files:
- split: train
path: "data/it-PH/*.parquet"
- config_name: "it-PK"
data_files:
- split: train
path: "data/it-PK/*.parquet"
- config_name: "it-PL"
data_files:
- split: train
path: "data/it-PL/*.parquet"
- config_name: "it-PT"
data_files:
- split: train
path: "data/it-PT/*.parquet"
- config_name: "it-PU"
data_files:
- split: train
path: "data/it-PU/*.parquet"
- config_name: "it-PW"
data_files:
- split: train
path: "data/it-PW/*.parquet"
- config_name: "it-PY"
data_files:
- split: train
path: "data/it-PY/*.parquet"
- config_name: "it-QA"
data_files:
- split: train
path: "data/it-QA/*.parquet"
- config_name: "it-RE"
data_files:
- split: train
path: "data/it-RE/*.parquet"
- config_name: "it-RO"
data_files:
- split: train
path: "data/it-RO/*.parquet"
- config_name: "it-RS"
data_files:
- split: train
path: "data/it-RS/*.parquet"
- config_name: "it-RU"
data_files:
- split: train
path: "data/it-RU/*.parquet"
- config_name: "it-SA"
data_files:
- split: train
path: "data/it-SA/*.parquet"
- config_name: "it-SE"
data_files:
- split: train
path: "data/it-SE/*.parquet"
- config_name: "it-SG"
data_files:
- split: train
path: "data/it-SG/*.parquet"
- config_name: "it-SI"
data_files:
- split: train
path: "data/it-SI/*.parquet"
- config_name: "it-SK"
data_files:
- split: train
path: "data/it-SK/*.parquet"
- config_name: "it-SM"
data_files:
- split: train
path: "data/it-SM/*.parquet"
- config_name: "it-SO"
data_files:
- split: train
path: "data/it-SO/*.parquet"
- config_name: "it-ST"
data_files:
- split: train
path: "data/it-ST/*.parquet"
- config_name: "it-SV"
data_files:
- split: train
path: "data/it-SV/*.parquet"
- config_name: "it-TH"
data_files:
- split: train
path: "data/it-TH/*.parquet"
- config_name: "it-TK"
data_files:
- split: train
path: "data/it-TK/*.parquet"
- config_name: "it-TL"
data_files:
- split: train
path: "data/it-TL/*.parquet"
- config_name: "it-TN"
data_files:
- split: train
path: "data/it-TN/*.parquet"
- config_name: "it-TO"
data_files:
- split: train
path: "data/it-TO/*.parquet"
- config_name: "it-TR"
data_files:
- split: train
path: "data/it-TR/*.parquet"
- config_name: "it-TT"
data_files:
- split: train
path: "data/it-TT/*.parquet"
- config_name: "it-TV"
data_files:
- split: train
path: "data/it-TV/*.parquet"
- config_name: "it-TW"
data_files:
- split: train
path: "data/it-TW/*.parquet"
- config_name: "it-TZ"
data_files:
- split: train
path: "data/it-TZ/*.parquet"
- config_name: "it-UA"
data_files:
- split: train
path: "data/it-UA/*.parquet"
- config_name: "it-UK"
data_files:
- split: train
path: "data/it-UK/*.parquet"
- config_name: "it-UM"
data_files:
- split: train
path: "data/it-UM/*.parquet"
- config_name: "it-US"
data_files:
- split: train
path: "data/it-US/*.parquet"
- config_name: "it-VA"
data_files:
- split: train
path: "data/it-VA/*.parquet"
- config_name: "it-VE"
data_files:
- split: train
path: "data/it-VE/*.parquet"
- config_name: "it-VN"
data_files:
- split: train
path: "data/it-VN/*.parquet"
- config_name: "it-WS"
data_files:
- split: train
path: "data/it-WS/*.parquet"
- config_name: "it-WW"
data_files:
- split: train
path: "data/it-WW/*.parquet"
- config_name: "it-XX"
data_files:
- split: train
path: "data/it-XX/*.parquet"
- config_name: "it-ZA"
data_files:
- split: train
path: "data/it-ZA/*.parquet"
- config_name: "ja-AE"
data_files:
- split: train
path: "data/ja-AE/*.parquet"
- config_name: "ja-AF"
data_files:
- split: train
path: "data/ja-AF/*.parquet"
- config_name: "ja-AI"
data_files:
- split: train
path: "data/ja-AI/*.parquet"
- config_name: "ja-AL"
data_files:
- split: train
path: "data/ja-AL/*.parquet"
- config_name: "ja-AM"
data_files:
- split: train
path: "data/ja-AM/*.parquet"
- config_name: "ja-AR"
data_files:
- split: train
path: "data/ja-AR/*.parquet"
- config_name: "ja-AS"
data_files:
- split: train
path: "data/ja-AS/*.parquet"
- config_name: "ja-AT"
data_files:
- split: train
path: "data/ja-AT/*.parquet"
- config_name: "ja-AU"
data_files:
- split: train
path: "data/ja-AU/*.parquet"
- config_name: "ja-AZ"
data_files:
- split: train
path: "data/ja-AZ/*.parquet"
- config_name: "ja-BA"
data_files:
- split: train
path: "data/ja-BA/*.parquet"
- config_name: "ja-BD"
data_files:
- split: train
path: "data/ja-BD/*.parquet"
- config_name: "ja-BE"
data_files:
- split: train
path: "data/ja-BE/*.parquet"
- config_name: "ja-BF"
data_files:
- split: train
path: "data/ja-BF/*.parquet"
- config_name: "ja-BG"
data_files:
- split: train
path: "data/ja-BG/*.parquet"
- config_name: "ja-BO"
data_files:
- split: train
path: "data/ja-BO/*.parquet"
- config_name: "ja-BR"
data_files:
- split: train
path: "data/ja-BR/*.parquet"
- config_name: "ja-BY"
data_files:
- split: train
path: "data/ja-BY/*.parquet"
- config_name: "ja-BZ"
data_files:
- split: train
path: "data/ja-BZ/*.parquet"
- config_name: "ja-CA"
data_files:
- split: train
path: "data/ja-CA/*.parquet"
- config_name: "ja-CC"
data_files:
- split: train
path: "data/ja-CC/*.parquet"
- config_name: "ja-CD"
data_files:
- split: train
path: "data/ja-CD/*.parquet"
- config_name: "ja-CF"
data_files:
- split: train
path: "data/ja-CF/*.parquet"
- config_name: "ja-CH"
data_files:
- split: train
path: "data/ja-CH/*.parquet"
- config_name: "ja-CL"
data_files:
- split: train
path: "data/ja-CL/*.parquet"
- config_name: "ja-CM"
data_files:
- split: train
path: "data/ja-CM/*.parquet"
- config_name: "ja-CN"
data_files:
- split: train
path: "data/ja-CN/*.parquet"
- config_name: "ja-CO"
data_files:
- split: train
path: "data/ja-CO/*.parquet"
- config_name: "ja-CR"
data_files:
- split: train
path: "data/ja-CR/*.parquet"
- config_name: "ja-CX"
data_files:
- split: train
path: "data/ja-CX/*.parquet"
- config_name: "ja-CZ"
data_files:
- split: train
path: "data/ja-CZ/*.parquet"
- config_name: "ja-DE"
data_files:
- split: train
path: "data/ja-DE/*.parquet"
- config_name: "ja-DK"
data_files:
- split: train
path: "data/ja-DK/*.parquet"
- config_name: "ja-DO"
data_files:
- split: train
path: "data/ja-DO/*.parquet"
- config_name: "ja-DZ"
data_files:
- split: train
path: "data/ja-DZ/*.parquet"
- config_name: "ja-EC"
data_files:
- split: train
path: "data/ja-EC/*.parquet"
- config_name: "ja-EE"
data_files:
- split: train
path: "data/ja-EE/*.parquet"
- config_name: "ja-EG"
data_files:
- split: train
path: "data/ja-EG/*.parquet"
- config_name: "ja-EN"
data_files:
- split: train
path: "data/ja-EN/*.parquet"
- config_name: "ja-ES"
data_files:
- split: train
path: "data/ja-ES/*.parquet"
- config_name: "ja-EU"
data_files:
- split: train
path: "data/ja-EU/*.parquet"
- config_name: "ja-FI"
data_files:
- split: train
path: "data/ja-FI/*.parquet"
- config_name: "ja-FJ"
data_files:
- split: train
path: "data/ja-FJ/*.parquet"
- config_name: "ja-FM"
data_files:
- split: train
path: "data/ja-FM/*.parquet"
- config_name: "ja-FR"
data_files:
- split: train
path: "data/ja-FR/*.parquet"
- config_name: "ja-GA"
data_files:
- split: train
path: "data/ja-GA/*.parquet"
- config_name: "ja-GB"
data_files:
- split: train
path: "data/ja-GB/*.parquet"
- config_name: "ja-GE"
data_files:
- split: train
path: "data/ja-GE/*.parquet"
- config_name: "ja-GG"
data_files:
- split: train
path: "data/ja-GG/*.parquet"
- config_name: "ja-GH"
data_files:
- split: train
path: "data/ja-GH/*.parquet"
- config_name: "ja-GQ"
data_files:
- split: train
path: "data/ja-GQ/*.parquet"
- config_name: "ja-GR"
data_files:
- split: train
path: "data/ja-GR/*.parquet"
- config_name: "ja-GT"
data_files:
- split: train
path: "data/ja-GT/*.parquet"
- config_name: "ja-HK"
data_files:
- split: train
path: "data/ja-HK/*.parquet"
- config_name: "ja-HR"
data_files:
- split: train
path: "data/ja-HR/*.parquet"
- config_name: "ja-HU"
data_files:
- split: train
path: "data/ja-HU/*.parquet"
- config_name: "ja-ID"
data_files:
- split: train
path: "data/ja-ID/*.parquet"
- config_name: "ja-IE"
data_files:
- split: train
path: "data/ja-IE/*.parquet"
- config_name: "ja-IL"
data_files:
- split: train
path: "data/ja-IL/*.parquet"
- config_name: "ja-IN"
data_files:
- split: train
path: "data/ja-IN/*.parquet"
- config_name: "ja-IO"
data_files:
- split: train
path: "data/ja-IO/*.parquet"
- config_name: "ja-IR"
data_files:
- split: train
path: "data/ja-IR/*.parquet"
- config_name: "ja-IS"
data_files:
- split: train
path: "data/ja-IS/*.parquet"
- config_name: "ja-IT"
data_files:
- split: train
path: "data/ja-IT/*.parquet"
- config_name: "ja-JA"
data_files:
- split: train
path: "data/ja-JA/*.parquet"
- config_name: "ja-JO"
data_files:
- split: train
path: "data/ja-JO/*.parquet"
- config_name: "ja-JP"
data_files:
- split: train
path: "data/ja-JP/*.parquet"
- config_name: "ja-KE"
data_files:
- split: train
path: "data/ja-KE/*.parquet"
- config_name: "ja-KG"
data_files:
- split: train
path: "data/ja-KG/*.parquet"
- config_name: "ja-KR"
data_files:
- split: train
path: "data/ja-KR/*.parquet"
- config_name: "ja-KZ"
data_files:
- split: train
path: "data/ja-KZ/*.parquet"
- config_name: "ja-LA"
data_files:
- split: train
path: "data/ja-LA/*.parquet"
- config_name: "ja-LB"
data_files:
- split: train
path: "data/ja-LB/*.parquet"
- config_name: "ja-LI"
data_files:
- split: train
path: "data/ja-LI/*.parquet"
- config_name: "ja-LK"
data_files:
- split: train
path: "data/ja-LK/*.parquet"
- config_name: "ja-LT"
data_files:
- split: train
path: "data/ja-LT/*.parquet"
- config_name: "ja-LU"
data_files:
- split: train
path: "data/ja-LU/*.parquet"
- config_name: "ja-LV"
data_files:
- split: train
path: "data/ja-LV/*.parquet"
- config_name: "ja-LY"
data_files:
- split: train
path: "data/ja-LY/*.parquet"
- config_name: "ja-MA"
data_files:
- split: train
path: "data/ja-MA/*.parquet"
- config_name: "ja-MD"
data_files:
- split: train
path: "data/ja-MD/*.parquet"
- config_name: "ja-ME"
data_files:
- split: train
path: "data/ja-ME/*.parquet"
- config_name: "ja-MG"
data_files:
- split: train
path: "data/ja-MG/*.parquet"
- config_name: "ja-MK"
data_files:
- split: train
path: "data/ja-MK/*.parquet"
- config_name: "ja-ML"
data_files:
- split: train
path: "data/ja-ML/*.parquet"
- config_name: "ja-MN"
data_files:
- split: train
path: "data/ja-MN/*.parquet"
- config_name: "ja-MQ"
data_files:
- split: train
path: "data/ja-MQ/*.parquet"
- config_name: "ja-MR"
data_files:
- split: train
path: "data/ja-MR/*.parquet"
- config_name: "ja-MS"
data_files:
- split: train
path: "data/ja-MS/*.parquet"
- config_name: "ja-MT"
data_files:
- split: train
path: "data/ja-MT/*.parquet"
- config_name: "ja-MU"
data_files:
- split: train
path: "data/ja-MU/*.parquet"
- config_name: "ja-MX"
data_files:
- split: train
path: "data/ja-MX/*.parquet"
- config_name: "ja-MY"
data_files:
- split: train
path: "data/ja-MY/*.parquet"
- config_name: "ja-MZ"
data_files:
- split: train
path: "data/ja-MZ/*.parquet"
- config_name: "ja-NF"
data_files:
- split: train
path: "data/ja-NF/*.parquet"
- config_name: "ja-NG"
data_files:
- split: train
path: "data/ja-NG/*.parquet"
- config_name: "ja-NL"
data_files:
- split: train
path: "data/ja-NL/*.parquet"
- config_name: "ja-NO"
data_files:
- split: train
path: "data/ja-NO/*.parquet"
- config_name: "ja-NP"
data_files:
- split: train
path: "data/ja-NP/*.parquet"
- config_name: "ja-NU"
data_files:
- split: train
path: "data/ja-NU/*.parquet"
- config_name: "ja-NZ"
data_files:
- split: train
path: "data/ja-NZ/*.parquet"
- config_name: "ja-PE"
data_files:
- split: train
path: "data/ja-PE/*.parquet"
- config_name: "ja-PH"
data_files:
- split: train
path: "data/ja-PH/*.parquet"
- config_name: "ja-PK"
data_files:
- split: train
path: "data/ja-PK/*.parquet"
- config_name: "ja-PL"
data_files:
- split: train
path: "data/ja-PL/*.parquet"
- config_name: "ja-PM"
data_files:
- split: train
path: "data/ja-PM/*.parquet"
- config_name: "ja-PS"
data_files:
- split: train
path: "data/ja-PS/*.parquet"
- config_name: "ja-PT"
data_files:
- split: train
path: "data/ja-PT/*.parquet"
- config_name: "ja-PW"
data_files:
- split: train
path: "data/ja-PW/*.parquet"
- config_name: "ja-PY"
data_files:
- split: train
path: "data/ja-PY/*.parquet"
- config_name: "ja-RE"
data_files:
- split: train
path: "data/ja-RE/*.parquet"
- config_name: "ja-RO"
data_files:
- split: train
path: "data/ja-RO/*.parquet"
- config_name: "ja-RS"
data_files:
- split: train
path: "data/ja-RS/*.parquet"
- config_name: "ja-RU"
data_files:
- split: train
path: "data/ja-RU/*.parquet"
- config_name: "ja-RW"
data_files:
- split: train
path: "data/ja-RW/*.parquet"
- config_name: "ja-SA"
data_files:
- split: train
path: "data/ja-SA/*.parquet"
- config_name: "ja-SC"
data_files:
- split: train
path: "data/ja-SC/*.parquet"
- config_name: "ja-SE"
data_files:
- split: train
path: "data/ja-SE/*.parquet"
- config_name: "ja-SG"
data_files:
- split: train
path: "data/ja-SG/*.parquet"
- config_name: "ja-SH"
data_files:
- split: train
path: "data/ja-SH/*.parquet"
- config_name: "ja-SI"
data_files:
- split: train
path: "data/ja-SI/*.parquet"
- config_name: "ja-SK"
data_files:
- split: train
path: "data/ja-SK/*.parquet"
- config_name: "ja-SN"
data_files:
- split: train
path: "data/ja-SN/*.parquet"
- config_name: "ja-SO"
data_files:
- split: train
path: "data/ja-SO/*.parquet"
- config_name: "ja-ST"
data_files:
- split: train
path: "data/ja-ST/*.parquet"
- config_name: "ja-SZ"
data_files:
- split: train
path: "data/ja-SZ/*.parquet"
- config_name: "ja-TC"
data_files:
- split: train
path: "data/ja-TC/*.parquet"
- config_name: "ja-TG"
data_files:
- split: train
path: "data/ja-TG/*.parquet"
- config_name: "ja-TH"
data_files:
- split: train
path: "data/ja-TH/*.parquet"
- config_name: "ja-TJ"
data_files:
- split: train
path: "data/ja-TJ/*.parquet"
- config_name: "ja-TK"
data_files:
- split: train
path: "data/ja-TK/*.parquet"
- config_name: "ja-TO"
data_files:
- split: train
path: "data/ja-TO/*.parquet"
- config_name: "ja-TR"
data_files:
- split: train
path: "data/ja-TR/*.parquet"
- config_name: "ja-TV"
data_files:
- split: train
path: "data/ja-TV/*.parquet"
- config_name: "ja-TW"
data_files:
- split: train
path: "data/ja-TW/*.parquet"
- config_name: "ja-TZ"
data_files:
- split: train
path: "data/ja-TZ/*.parquet"
- config_name: "ja-UA"
data_files:
- split: train
path: "data/ja-UA/*.parquet"
- config_name: "ja-UG"
data_files:
- split: train
path: "data/ja-UG/*.parquet"
- config_name: "ja-US"
data_files:
- split: train
path: "data/ja-US/*.parquet"
- config_name: "ja-UY"
data_files:
- split: train
path: "data/ja-UY/*.parquet"
- config_name: "ja-UZ"
data_files:
- split: train
path: "data/ja-UZ/*.parquet"
- config_name: "ja-VC"
data_files:
- split: train
path: "data/ja-VC/*.parquet"
- config_name: "ja-VE"
data_files:
- split: train
path: "data/ja-VE/*.parquet"
- config_name: "ja-VG"
data_files:
- split: train
path: "data/ja-VG/*.parquet"
- config_name: "ja-VN"
data_files:
- split: train
path: "data/ja-VN/*.parquet"
- config_name: "ja-WS"
data_files:
- split: train
path: "data/ja-WS/*.parquet"
- config_name: "ja-XX"
data_files:
- split: train
path: "data/ja-XX/*.parquet"
- config_name: "ja-ZA"
data_files:
- split: train
path: "data/ja-ZA/*.parquet"
- config_name: "ja-ZM"
data_files:
- split: train
path: "data/ja-ZM/*.parquet"
- config_name: "ja-ZW"
data_files:
- split: train
path: "data/ja-ZW/*.parquet"
- config_name: "jbo-XX"
data_files:
- split: train
path: "data/jbo-XX/*.parquet"
- config_name: "jv-XX"
data_files:
- split: train
path: "data/jv-XX/*.parquet"
- config_name: "ka-AM"
data_files:
- split: train
path: "data/ka-AM/*.parquet"
- config_name: "ka-AZ"
data_files:
- split: train
path: "data/ka-AZ/*.parquet"
- config_name: "ka-CC"
data_files:
- split: train
path: "data/ka-CC/*.parquet"
- config_name: "ka-CO"
data_files:
- split: train
path: "data/ka-CO/*.parquet"
- config_name: "ka-DE"
data_files:
- split: train
path: "data/ka-DE/*.parquet"
- config_name: "ka-EU"
data_files:
- split: train
path: "data/ka-EU/*.parquet"
- config_name: "ka-GB"
data_files:
- split: train
path: "data/ka-GB/*.parquet"
- config_name: "ka-GE"
data_files:
- split: train
path: "data/ka-GE/*.parquet"
- config_name: "ka-IN"
data_files:
- split: train
path: "data/ka-IN/*.parquet"
- config_name: "ka-IO"
data_files:
- split: train
path: "data/ka-IO/*.parquet"
- config_name: "ka-IR"
data_files:
- split: train
path: "data/ka-IR/*.parquet"
- config_name: "ka-JP"
data_files:
- split: train
path: "data/ka-JP/*.parquet"
- config_name: "ka-KA"
data_files:
- split: train
path: "data/ka-KA/*.parquet"
- config_name: "ka-KZ"
data_files:
- split: train
path: "data/ka-KZ/*.parquet"
- config_name: "ka-ME"
data_files:
- split: train
path: "data/ka-ME/*.parquet"
- config_name: "ka-RS"
data_files:
- split: train
path: "data/ka-RS/*.parquet"
- config_name: "ka-RU"
data_files:
- split: train
path: "data/ka-RU/*.parquet"
- config_name: "ka-SK"
data_files:
- split: train
path: "data/ka-SK/*.parquet"
- config_name: "ka-TO"
data_files:
- split: train
path: "data/ka-TO/*.parquet"
- config_name: "ka-TR"
data_files:
- split: train
path: "data/ka-TR/*.parquet"
- config_name: "ka-TV"
data_files:
- split: train
path: "data/ka-TV/*.parquet"
- config_name: "ka-UA"
data_files:
- split: train
path: "data/ka-UA/*.parquet"
- config_name: "ka-US"
data_files:
- split: train
path: "data/ka-US/*.parquet"
- config_name: "ka-WS"
data_files:
- split: train
path: "data/ka-WS/*.parquet"
- config_name: "ka-XX"
data_files:
- split: train
path: "data/ka-XX/*.parquet"
- config_name: "kk-AI"
data_files:
- split: train
path: "data/kk-AI/*.parquet"
- config_name: "kk-BR"
data_files:
- split: train
path: "data/kk-BR/*.parquet"
- config_name: "kk-CN"
data_files:
- split: train
path: "data/kk-CN/*.parquet"
- config_name: "kk-DE"
data_files:
- split: train
path: "data/kk-DE/*.parquet"
- config_name: "kk-EU"
data_files:
- split: train
path: "data/kk-EU/*.parquet"
- config_name: "kk-FM"
data_files:
- split: train
path: "data/kk-FM/*.parquet"
- config_name: "kk-FR"
data_files:
- split: train
path: "data/kk-FR/*.parquet"
- config_name: "kk-GB"
data_files:
- split: train
path: "data/kk-GB/*.parquet"
- config_name: "kk-HK"
data_files:
- split: train
path: "data/kk-HK/*.parquet"
- config_name: "kk-IN"
data_files:
- split: train
path: "data/kk-IN/*.parquet"
- config_name: "kk-KG"
data_files:
- split: train
path: "data/kk-KG/*.parquet"
- config_name: "kk-KK"
data_files:
- split: train
path: "data/kk-KK/*.parquet"
- config_name: "kk-KZ"
data_files:
- split: train
path: "data/kk-KZ/*.parquet"
- config_name: "kk-ME"
data_files:
- split: train
path: "data/kk-ME/*.parquet"
- config_name: "kk-PE"
data_files:
- split: train
path: "data/kk-PE/*.parquet"
- config_name: "kk-QR"
data_files:
- split: train
path: "data/kk-QR/*.parquet"
- config_name: "kk-RU"
data_files:
- split: train
path: "data/kk-RU/*.parquet"
- config_name: "kk-SE"
data_files:
- split: train
path: "data/kk-SE/*.parquet"
- config_name: "kk-SG"
data_files:
- split: train
path: "data/kk-SG/*.parquet"
- config_name: "kk-TR"
data_files:
- split: train
path: "data/kk-TR/*.parquet"
- config_name: "kk-TV"
data_files:
- split: train
path: "data/kk-TV/*.parquet"
- config_name: "kk-UA"
data_files:
- split: train
path: "data/kk-UA/*.parquet"
- config_name: "kk-US"
data_files:
- split: train
path: "data/kk-US/*.parquet"
- config_name: "kk-UZ"
data_files:
- split: train
path: "data/kk-UZ/*.parquet"
- config_name: "kk-WS"
data_files:
- split: train
path: "data/kk-WS/*.parquet"
- config_name: "kk-XX"
data_files:
- split: train
path: "data/kk-XX/*.parquet"
- config_name: "km-AU"
data_files:
- split: train
path: "data/km-AU/*.parquet"
- config_name: "km-CN"
data_files:
- split: train
path: "data/km-CN/*.parquet"
- config_name: "km-ES"
data_files:
- split: train
path: "data/km-ES/*.parquet"
- config_name: "km-FR"
data_files:
- split: train
path: "data/km-FR/*.parquet"
- config_name: "km-KH"
data_files:
- split: train
path: "data/km-KH/*.parquet"
- config_name: "km-TV"
data_files:
- split: train
path: "data/km-TV/*.parquet"
- config_name: "km-US"
data_files:
- split: train
path: "data/km-US/*.parquet"
- config_name: "km-VN"
data_files:
- split: train
path: "data/km-VN/*.parquet"
- config_name: "km-XX"
data_files:
- split: train
path: "data/km-XX/*.parquet"
- config_name: "kn-GB"
data_files:
- split: train
path: "data/kn-GB/*.parquet"
- config_name: "kn-IN"
data_files:
- split: train
path: "data/kn-IN/*.parquet"
- config_name: "kn-RU"
data_files:
- split: train
path: "data/kn-RU/*.parquet"
- config_name: "kn-US"
data_files:
- split: train
path: "data/kn-US/*.parquet"
- config_name: "kn-XX"
data_files:
- split: train
path: "data/kn-XX/*.parquet"
- config_name: "ko-AE"
data_files:
- split: train
path: "data/ko-AE/*.parquet"
- config_name: "ko-AI"
data_files:
- split: train
path: "data/ko-AI/*.parquet"
- config_name: "ko-AM"
data_files:
- split: train
path: "data/ko-AM/*.parquet"
- config_name: "ko-AR"
data_files:
- split: train
path: "data/ko-AR/*.parquet"
- config_name: "ko-AT"
data_files:
- split: train
path: "data/ko-AT/*.parquet"
- config_name: "ko-AU"
data_files:
- split: train
path: "data/ko-AU/*.parquet"
- config_name: "ko-BE"
data_files:
- split: train
path: "data/ko-BE/*.parquet"
- config_name: "ko-BG"
data_files:
- split: train
path: "data/ko-BG/*.parquet"
- config_name: "ko-BO"
data_files:
- split: train
path: "data/ko-BO/*.parquet"
- config_name: "ko-BR"
data_files:
- split: train
path: "data/ko-BR/*.parquet"
- config_name: "ko-BZ"
data_files:
- split: train
path: "data/ko-BZ/*.parquet"
- config_name: "ko-CA"
data_files:
- split: train
path: "data/ko-CA/*.parquet"
- config_name: "ko-CC"
data_files:
- split: train
path: "data/ko-CC/*.parquet"
- config_name: "ko-CD"
data_files:
- split: train
path: "data/ko-CD/*.parquet"
- config_name: "ko-CH"
data_files:
- split: train
path: "data/ko-CH/*.parquet"
- config_name: "ko-CL"
data_files:
- split: train
path: "data/ko-CL/*.parquet"
- config_name: "ko-CN"
data_files:
- split: train
path: "data/ko-CN/*.parquet"
- config_name: "ko-CO"
data_files:
- split: train
path: "data/ko-CO/*.parquet"
- config_name: "ko-CZ"
data_files:
- split: train
path: "data/ko-CZ/*.parquet"
- config_name: "ko-DE"
data_files:
- split: train
path: "data/ko-DE/*.parquet"
- config_name: "ko-DK"
data_files:
- split: train
path: "data/ko-DK/*.parquet"
- config_name: "ko-DO"
data_files:
- split: train
path: "data/ko-DO/*.parquet"
- config_name: "ko-EC"
data_files:
- split: train
path: "data/ko-EC/*.parquet"
- config_name: "ko-EN"
data_files:
- split: train
path: "data/ko-EN/*.parquet"
- config_name: "ko-ES"
data_files:
- split: train
path: "data/ko-ES/*.parquet"
- config_name: "ko-EU"
data_files:
- split: train
path: "data/ko-EU/*.parquet"
- config_name: "ko-FI"
data_files:
- split: train
path: "data/ko-FI/*.parquet"
- config_name: "ko-FM"
data_files:
- split: train
path: "data/ko-FM/*.parquet"
- config_name: "ko-FR"
data_files:
- split: train
path: "data/ko-FR/*.parquet"
- config_name: "ko-GB"
data_files:
- split: train
path: "data/ko-GB/*.parquet"
- config_name: "ko-GR"
data_files:
- split: train
path: "data/ko-GR/*.parquet"
- config_name: "ko-HK"
data_files:
- split: train
path: "data/ko-HK/*.parquet"
- config_name: "ko-HR"
data_files:
- split: train
path: "data/ko-HR/*.parquet"
- config_name: "ko-HU"
data_files:
- split: train
path: "data/ko-HU/*.parquet"
- config_name: "ko-ID"
data_files:
- split: train
path: "data/ko-ID/*.parquet"
- config_name: "ko-IE"
data_files:
- split: train
path: "data/ko-IE/*.parquet"
- config_name: "ko-IM"
data_files:
- split: train
path: "data/ko-IM/*.parquet"
- config_name: "ko-IN"
data_files:
- split: train
path: "data/ko-IN/*.parquet"
- config_name: "ko-IO"
data_files:
- split: train
path: "data/ko-IO/*.parquet"
- config_name: "ko-IR"
data_files:
- split: train
path: "data/ko-IR/*.parquet"
- config_name: "ko-IS"
data_files:
- split: train
path: "data/ko-IS/*.parquet"
- config_name: "ko-IT"
data_files:
- split: train
path: "data/ko-IT/*.parquet"
- config_name: "ko-JP"
data_files:
- split: train
path: "data/ko-JP/*.parquet"
- config_name: "ko-KH"
data_files:
- split: train
path: "data/ko-KH/*.parquet"
- config_name: "ko-KO"
data_files:
- split: train
path: "data/ko-KO/*.parquet"
- config_name: "ko-KP"
data_files:
- split: train
path: "data/ko-KP/*.parquet"
- config_name: "ko-KR"
data_files:
- split: train
path: "data/ko-KR/*.parquet"
- config_name: "ko-KY"
data_files:
- split: train
path: "data/ko-KY/*.parquet"
- config_name: "ko-LY"
data_files:
- split: train
path: "data/ko-LY/*.parquet"
- config_name: "ko-MA"
data_files:
- split: train
path: "data/ko-MA/*.parquet"
- config_name: "ko-ME"
data_files:
- split: train
path: "data/ko-ME/*.parquet"
- config_name: "ko-MO"
data_files:
- split: train
path: "data/ko-MO/*.parquet"
- config_name: "ko-MX"
data_files:
- split: train
path: "data/ko-MX/*.parquet"
- config_name: "ko-MY"
data_files:
- split: train
path: "data/ko-MY/*.parquet"
- config_name: "ko-NG"
data_files:
- split: train
path: "data/ko-NG/*.parquet"
- config_name: "ko-NL"
data_files:
- split: train
path: "data/ko-NL/*.parquet"
- config_name: "ko-NO"
data_files:
- split: train
path: "data/ko-NO/*.parquet"
- config_name: "ko-NZ"
data_files:
- split: train
path: "data/ko-NZ/*.parquet"
- config_name: "ko-PE"
data_files:
- split: train
path: "data/ko-PE/*.parquet"
- config_name: "ko-PH"
data_files:
- split: train
path: "data/ko-PH/*.parquet"
- config_name: "ko-PK"
data_files:
- split: train
path: "data/ko-PK/*.parquet"
- config_name: "ko-PL"
data_files:
- split: train
path: "data/ko-PL/*.parquet"
- config_name: "ko-PT"
data_files:
- split: train
path: "data/ko-PT/*.parquet"
- config_name: "ko-PW"
data_files:
- split: train
path: "data/ko-PW/*.parquet"
- config_name: "ko-PY"
data_files:
- split: train
path: "data/ko-PY/*.parquet"
- config_name: "ko-RE"
data_files:
- split: train
path: "data/ko-RE/*.parquet"
- config_name: "ko-RO"
data_files:
- split: train
path: "data/ko-RO/*.parquet"
- config_name: "ko-RS"
data_files:
- split: train
path: "data/ko-RS/*.parquet"
- config_name: "ko-RU"
data_files:
- split: train
path: "data/ko-RU/*.parquet"
- config_name: "ko-SE"
data_files:
- split: train
path: "data/ko-SE/*.parquet"
- config_name: "ko-SG"
data_files:
- split: train
path: "data/ko-SG/*.parquet"
- config_name: "ko-SH"
data_files:
- split: train
path: "data/ko-SH/*.parquet"
- config_name: "ko-SI"
data_files:
- split: train
path: "data/ko-SI/*.parquet"
- config_name: "ko-SO"
data_files:
- split: train
path: "data/ko-SO/*.parquet"
- config_name: "ko-TC"
data_files:
- split: train
path: "data/ko-TC/*.parquet"
- config_name: "ko-TH"
data_files:
- split: train
path: "data/ko-TH/*.parquet"
- config_name: "ko-TK"
data_files:
- split: train
path: "data/ko-TK/*.parquet"
- config_name: "ko-TO"
data_files:
- split: train
path: "data/ko-TO/*.parquet"
- config_name: "ko-TR"
data_files:
- split: train
path: "data/ko-TR/*.parquet"
- config_name: "ko-TV"
data_files:
- split: train
path: "data/ko-TV/*.parquet"
- config_name: "ko-TW"
data_files:
- split: train
path: "data/ko-TW/*.parquet"
- config_name: "ko-UA"
data_files:
- split: train
path: "data/ko-UA/*.parquet"
- config_name: "ko-US"
data_files:
- split: train
path: "data/ko-US/*.parquet"
- config_name: "ko-VA"
data_files:
- split: train
path: "data/ko-VA/*.parquet"
- config_name: "ko-VN"
data_files:
- split: train
path: "data/ko-VN/*.parquet"
- config_name: "ko-WS"
data_files:
- split: train
path: "data/ko-WS/*.parquet"
- config_name: "ko-WW"
data_files:
- split: train
path: "data/ko-WW/*.parquet"
- config_name: "ko-XX"
data_files:
- split: train
path: "data/ko-XX/*.parquet"
- config_name: "krc-RU"
data_files:
- split: train
path: "data/krc-RU/*.parquet"
- config_name: "krc-XX"
data_files:
- split: train
path: "data/krc-XX/*.parquet"
- config_name: "ku-BE"
data_files:
- split: train
path: "data/ku-BE/*.parquet"
- config_name: "ku-DE"
data_files:
- split: train
path: "data/ku-DE/*.parquet"
- config_name: "ku-DK"
data_files:
- split: train
path: "data/ku-DK/*.parquet"
- config_name: "ku-GB"
data_files:
- split: train
path: "data/ku-GB/*.parquet"
- config_name: "ku-KR"
data_files:
- split: train
path: "data/ku-KR/*.parquet"
- config_name: "ku-KU"
data_files:
- split: train
path: "data/ku-KU/*.parquet"
- config_name: "ku-NL"
data_files:
- split: train
path: "data/ku-NL/*.parquet"
- config_name: "ku-RU"
data_files:
- split: train
path: "data/ku-RU/*.parquet"
- config_name: "ku-SE"
data_files:
- split: train
path: "data/ku-SE/*.parquet"
- config_name: "ku-TR"
data_files:
- split: train
path: "data/ku-TR/*.parquet"
- config_name: "ku-TV"
data_files:
- split: train
path: "data/ku-TV/*.parquet"
- config_name: "ku-US"
data_files:
- split: train
path: "data/ku-US/*.parquet"
- config_name: "ku-XX"
data_files:
- split: train
path: "data/ku-XX/*.parquet"
- config_name: "kv-XX"
data_files:
- split: train
path: "data/kv-XX/*.parquet"
- config_name: "kw-IM"
data_files:
- split: train
path: "data/kw-IM/*.parquet"
- config_name: "kw-XX"
data_files:
- split: train
path: "data/kw-XX/*.parquet"
- config_name: "ky-BG"
data_files:
- split: train
path: "data/ky-BG/*.parquet"
- config_name: "ky-EU"
data_files:
- split: train
path: "data/ky-EU/*.parquet"
- config_name: "ky-FR"
data_files:
- split: train
path: "data/ky-FR/*.parquet"
- config_name: "ky-GB"
data_files:
- split: train
path: "data/ky-GB/*.parquet"
- config_name: "ky-IO"
data_files:
- split: train
path: "data/ky-IO/*.parquet"
- config_name: "ky-KG"
data_files:
- split: train
path: "data/ky-KG/*.parquet"
- config_name: "ky-KY"
data_files:
- split: train
path: "data/ky-KY/*.parquet"
- config_name: "ky-KZ"
data_files:
- split: train
path: "data/ky-KZ/*.parquet"
- config_name: "ky-RU"
data_files:
- split: train
path: "data/ky-RU/*.parquet"
- config_name: "ky-TV"
data_files:
- split: train
path: "data/ky-TV/*.parquet"
- config_name: "ky-US"
data_files:
- split: train
path: "data/ky-US/*.parquet"
- config_name: "ky-UZ"
data_files:
- split: train
path: "data/ky-UZ/*.parquet"
- config_name: "ky-XX"
data_files:
- split: train
path: "data/ky-XX/*.parquet"
- config_name: "la-AR"
data_files:
- split: train
path: "data/la-AR/*.parquet"
- config_name: "la-AU"
data_files:
- split: train
path: "data/la-AU/*.parquet"
- config_name: "la-BE"
data_files:
- split: train
path: "data/la-BE/*.parquet"
- config_name: "la-BR"
data_files:
- split: train
path: "data/la-BR/*.parquet"
- config_name: "la-CH"
data_files:
- split: train
path: "data/la-CH/*.parquet"
- config_name: "la-CN"
data_files:
- split: train
path: "data/la-CN/*.parquet"
- config_name: "la-CO"
data_files:
- split: train
path: "data/la-CO/*.parquet"
- config_name: "la-DE"
data_files:
- split: train
path: "data/la-DE/*.parquet"
- config_name: "la-DK"
data_files:
- split: train
path: "data/la-DK/*.parquet"
- config_name: "la-ES"
data_files:
- split: train
path: "data/la-ES/*.parquet"
- config_name: "la-FI"
data_files:
- split: train
path: "data/la-FI/*.parquet"
- config_name: "la-FR"
data_files:
- split: train
path: "data/la-FR/*.parquet"
- config_name: "la-GB"
data_files:
- split: train
path: "data/la-GB/*.parquet"
- config_name: "la-ID"
data_files:
- split: train
path: "data/la-ID/*.parquet"
- config_name: "la-IO"
data_files:
- split: train
path: "data/la-IO/*.parquet"
- config_name: "la-IS"
data_files:
- split: train
path: "data/la-IS/*.parquet"
- config_name: "la-IT"
data_files:
- split: train
path: "data/la-IT/*.parquet"
- config_name: "la-LK"
data_files:
- split: train
path: "data/la-LK/*.parquet"
- config_name: "la-ME"
data_files:
- split: train
path: "data/la-ME/*.parquet"
- config_name: "la-MX"
data_files:
- split: train
path: "data/la-MX/*.parquet"
- config_name: "la-NL"
data_files:
- split: train
path: "data/la-NL/*.parquet"
- config_name: "la-SI"
data_files:
- split: train
path: "data/la-SI/*.parquet"
- config_name: "la-US"
data_files:
- split: train
path: "data/la-US/*.parquet"
- config_name: "la-VN"
data_files:
- split: train
path: "data/la-VN/*.parquet"
- config_name: "la-XX"
data_files:
- split: train
path: "data/la-XX/*.parquet"
- config_name: "lb-BE"
data_files:
- split: train
path: "data/lb-BE/*.parquet"
- config_name: "lb-DE"
data_files:
- split: train
path: "data/lb-DE/*.parquet"
- config_name: "lb-EU"
data_files:
- split: train
path: "data/lb-EU/*.parquet"
- config_name: "lb-FR"
data_files:
- split: train
path: "data/lb-FR/*.parquet"
- config_name: "lb-HR"
data_files:
- split: train
path: "data/lb-HR/*.parquet"
- config_name: "lb-IE"
data_files:
- split: train
path: "data/lb-IE/*.parquet"
- config_name: "lb-LU"
data_files:
- split: train
path: "data/lb-LU/*.parquet"
- config_name: "lb-US"
data_files:
- split: train
path: "data/lb-US/*.parquet"
- config_name: "lb-XX"
data_files:
- split: train
path: "data/lb-XX/*.parquet"
- config_name: "lez-RU"
data_files:
- split: train
path: "data/lez-RU/*.parquet"
- config_name: "lez-XX"
data_files:
- split: train
path: "data/lez-XX/*.parquet"
- config_name: "li-XX"
data_files:
- split: train
path: "data/li-XX/*.parquet"
- config_name: "lmo-XX"
data_files:
- split: train
path: "data/lmo-XX/*.parquet"
- config_name: "lo-CN"
data_files:
- split: train
path: "data/lo-CN/*.parquet"
- config_name: "lo-ES"
data_files:
- split: train
path: "data/lo-ES/*.parquet"
- config_name: "lo-GB"
data_files:
- split: train
path: "data/lo-GB/*.parquet"
- config_name: "lo-LA"
data_files:
- split: train
path: "data/lo-LA/*.parquet"
- config_name: "lo-SI"
data_files:
- split: train
path: "data/lo-SI/*.parquet"
- config_name: "lo-US"
data_files:
- split: train
path: "data/lo-US/*.parquet"
- config_name: "lo-VN"
data_files:
- split: train
path: "data/lo-VN/*.parquet"
- config_name: "lo-XX"
data_files:
- split: train
path: "data/lo-XX/*.parquet"
- config_name: "lt-AI"
data_files:
- split: train
path: "data/lt-AI/*.parquet"
- config_name: "lt-AM"
data_files:
- split: train
path: "data/lt-AM/*.parquet"
- config_name: "lt-AT"
data_files:
- split: train
path: "data/lt-AT/*.parquet"
- config_name: "lt-BM"
data_files:
- split: train
path: "data/lt-BM/*.parquet"
- config_name: "lt-BR"
data_files:
- split: train
path: "data/lt-BR/*.parquet"
- config_name: "lt-CA"
data_files:
- split: train
path: "data/lt-CA/*.parquet"
- config_name: "lt-CF"
data_files:
- split: train
path: "data/lt-CF/*.parquet"
- config_name: "lt-CH"
data_files:
- split: train
path: "data/lt-CH/*.parquet"
- config_name: "lt-CN"
data_files:
- split: train
path: "data/lt-CN/*.parquet"
- config_name: "lt-CO"
data_files:
- split: train
path: "data/lt-CO/*.parquet"
- config_name: "lt-CZ"
data_files:
- split: train
path: "data/lt-CZ/*.parquet"
- config_name: "lt-DE"
data_files:
- split: train
path: "data/lt-DE/*.parquet"
- config_name: "lt-DK"
data_files:
- split: train
path: "data/lt-DK/*.parquet"
- config_name: "lt-EE"
data_files:
- split: train
path: "data/lt-EE/*.parquet"
- config_name: "lt-EN"
data_files:
- split: train
path: "data/lt-EN/*.parquet"
- config_name: "lt-ES"
data_files:
- split: train
path: "data/lt-ES/*.parquet"
- config_name: "lt-EU"
data_files:
- split: train
path: "data/lt-EU/*.parquet"
- config_name: "lt-FI"
data_files:
- split: train
path: "data/lt-FI/*.parquet"
- config_name: "lt-FM"
data_files:
- split: train
path: "data/lt-FM/*.parquet"
- config_name: "lt-FR"
data_files:
- split: train
path: "data/lt-FR/*.parquet"
- config_name: "lt-GB"
data_files:
- split: train
path: "data/lt-GB/*.parquet"
- config_name: "lt-IN"
data_files:
- split: train
path: "data/lt-IN/*.parquet"
- config_name: "lt-IO"
data_files:
- split: train
path: "data/lt-IO/*.parquet"
- config_name: "lt-IT"
data_files:
- split: train
path: "data/lt-IT/*.parquet"
- config_name: "lt-JP"
data_files:
- split: train
path: "data/lt-JP/*.parquet"
- config_name: "lt-LT"
data_files:
- split: train
path: "data/lt-LT/*.parquet"
- config_name: "lt-LU"
data_files:
- split: train
path: "data/lt-LU/*.parquet"
- config_name: "lt-LV"
data_files:
- split: train
path: "data/lt-LV/*.parquet"
- config_name: "lt-NL"
data_files:
- split: train
path: "data/lt-NL/*.parquet"
- config_name: "lt-NO"
data_files:
- split: train
path: "data/lt-NO/*.parquet"
- config_name: "lt-PL"
data_files:
- split: train
path: "data/lt-PL/*.parquet"
- config_name: "lt-PT"
data_files:
- split: train
path: "data/lt-PT/*.parquet"
- config_name: "lt-RO"
data_files:
- split: train
path: "data/lt-RO/*.parquet"
- config_name: "lt-RU"
data_files:
- split: train
path: "data/lt-RU/*.parquet"
- config_name: "lt-SE"
data_files:
- split: train
path: "data/lt-SE/*.parquet"
- config_name: "lt-SI"
data_files:
- split: train
path: "data/lt-SI/*.parquet"
- config_name: "lt-TV"
data_files:
- split: train
path: "data/lt-TV/*.parquet"
- config_name: "lt-UA"
data_files:
- split: train
path: "data/lt-UA/*.parquet"
- config_name: "lt-US"
data_files:
- split: train
path: "data/lt-US/*.parquet"
- config_name: "lt-VA"
data_files:
- split: train
path: "data/lt-VA/*.parquet"
- config_name: "lt-XX"
data_files:
- split: train
path: "data/lt-XX/*.parquet"
- config_name: "lv-AI"
data_files:
- split: train
path: "data/lv-AI/*.parquet"
- config_name: "lv-AM"
data_files:
- split: train
path: "data/lv-AM/*.parquet"
- config_name: "lv-AU"
data_files:
- split: train
path: "data/lv-AU/*.parquet"
- config_name: "lv-BE"
data_files:
- split: train
path: "data/lv-BE/*.parquet"
- config_name: "lv-CA"
data_files:
- split: train
path: "data/lv-CA/*.parquet"
- config_name: "lv-CH"
data_files:
- split: train
path: "data/lv-CH/*.parquet"
- config_name: "lv-CO"
data_files:
- split: train
path: "data/lv-CO/*.parquet"
- config_name: "lv-DE"
data_files:
- split: train
path: "data/lv-DE/*.parquet"
- config_name: "lv-EE"
data_files:
- split: train
path: "data/lv-EE/*.parquet"
- config_name: "lv-EU"
data_files:
- split: train
path: "data/lv-EU/*.parquet"
- config_name: "lv-FI"
data_files:
- split: train
path: "data/lv-FI/*.parquet"
- config_name: "lv-FM"
data_files:
- split: train
path: "data/lv-FM/*.parquet"
- config_name: "lv-FR"
data_files:
- split: train
path: "data/lv-FR/*.parquet"
- config_name: "lv-GB"
data_files:
- split: train
path: "data/lv-GB/*.parquet"
- config_name: "lv-IE"
data_files:
- split: train
path: "data/lv-IE/*.parquet"
- config_name: "lv-IO"
data_files:
- split: train
path: "data/lv-IO/*.parquet"
- config_name: "lv-LG"
data_files:
- split: train
path: "data/lv-LG/*.parquet"
- config_name: "lv-LT"
data_files:
- split: train
path: "data/lv-LT/*.parquet"
- config_name: "lv-LV"
data_files:
- split: train
path: "data/lv-LV/*.parquet"
- config_name: "lv-ME"
data_files:
- split: train
path: "data/lv-ME/*.parquet"
- config_name: "lv-NL"
data_files:
- split: train
path: "data/lv-NL/*.parquet"
- config_name: "lv-NO"
data_files:
- split: train
path: "data/lv-NO/*.parquet"
- config_name: "lv-PL"
data_files:
- split: train
path: "data/lv-PL/*.parquet"
- config_name: "lv-PW"
data_files:
- split: train
path: "data/lv-PW/*.parquet"
- config_name: "lv-RO"
data_files:
- split: train
path: "data/lv-RO/*.parquet"
- config_name: "lv-RU"
data_files:
- split: train
path: "data/lv-RU/*.parquet"
- config_name: "lv-SE"
data_files:
- split: train
path: "data/lv-SE/*.parquet"
- config_name: "lv-TV"
data_files:
- split: train
path: "data/lv-TV/*.parquet"
- config_name: "lv-US"
data_files:
- split: train
path: "data/lv-US/*.parquet"
- config_name: "lv-VA"
data_files:
- split: train
path: "data/lv-VA/*.parquet"
- config_name: "lv-WS"
data_files:
- split: train
path: "data/lv-WS/*.parquet"
- config_name: "lv-XX"
data_files:
- split: train
path: "data/lv-XX/*.parquet"
- config_name: "mg-ES"
data_files:
- split: train
path: "data/mg-ES/*.parquet"
- config_name: "mg-FR"
data_files:
- split: train
path: "data/mg-FR/*.parquet"
- config_name: "mg-GB"
data_files:
- split: train
path: "data/mg-GB/*.parquet"
- config_name: "mg-IN"
data_files:
- split: train
path: "data/mg-IN/*.parquet"
- config_name: "mg-MG"
data_files:
- split: train
path: "data/mg-MG/*.parquet"
- config_name: "mg-TO"
data_files:
- split: train
path: "data/mg-TO/*.parquet"
- config_name: "mg-US"
data_files:
- split: train
path: "data/mg-US/*.parquet"
- config_name: "mg-XX"
data_files:
- split: train
path: "data/mg-XX/*.parquet"
- config_name: "mhr-RU"
data_files:
- split: train
path: "data/mhr-RU/*.parquet"
- config_name: "mhr-XX"
data_files:
- split: train
path: "data/mhr-XX/*.parquet"
- config_name: "min-XX"
data_files:
- split: train
path: "data/min-XX/*.parquet"
- config_name: "mk-AL"
data_files:
- split: train
path: "data/mk-AL/*.parquet"
- config_name: "mk-AT"
data_files:
- split: train
path: "data/mk-AT/*.parquet"
- config_name: "mk-AU"
data_files:
- split: train
path: "data/mk-AU/*.parquet"
- config_name: "mk-BA"
data_files:
- split: train
path: "data/mk-BA/*.parquet"
- config_name: "mk-BG"
data_files:
- split: train
path: "data/mk-BG/*.parquet"
- config_name: "mk-BY"
data_files:
- split: train
path: "data/mk-BY/*.parquet"
- config_name: "mk-CC"
data_files:
- split: train
path: "data/mk-CC/*.parquet"
- config_name: "mk-CN"
data_files:
- split: train
path: "data/mk-CN/*.parquet"
- config_name: "mk-CO"
data_files:
- split: train
path: "data/mk-CO/*.parquet"
- config_name: "mk-DE"
data_files:
- split: train
path: "data/mk-DE/*.parquet"
- config_name: "mk-EU"
data_files:
- split: train
path: "data/mk-EU/*.parquet"
- config_name: "mk-FR"
data_files:
- split: train
path: "data/mk-FR/*.parquet"
- config_name: "mk-GB"
data_files:
- split: train
path: "data/mk-GB/*.parquet"
- config_name: "mk-GR"
data_files:
- split: train
path: "data/mk-GR/*.parquet"
- config_name: "mk-IS"
data_files:
- split: train
path: "data/mk-IS/*.parquet"
- config_name: "mk-IT"
data_files:
- split: train
path: "data/mk-IT/*.parquet"
- config_name: "mk-ME"
data_files:
- split: train
path: "data/mk-ME/*.parquet"
- config_name: "mk-MK"
data_files:
- split: train
path: "data/mk-MK/*.parquet"
- config_name: "mk-NU"
data_files:
- split: train
path: "data/mk-NU/*.parquet"
- config_name: "mk-PT"
data_files:
- split: train
path: "data/mk-PT/*.parquet"
- config_name: "mk-RO"
data_files:
- split: train
path: "data/mk-RO/*.parquet"
- config_name: "mk-RS"
data_files:
- split: train
path: "data/mk-RS/*.parquet"
- config_name: "mk-RU"
data_files:
- split: train
path: "data/mk-RU/*.parquet"
- config_name: "mk-TV"
data_files:
- split: train
path: "data/mk-TV/*.parquet"
- config_name: "mk-UA"
data_files:
- split: train
path: "data/mk-UA/*.parquet"
- config_name: "mk-US"
data_files:
- split: train
path: "data/mk-US/*.parquet"
- config_name: "mk-VA"
data_files:
- split: train
path: "data/mk-VA/*.parquet"
- config_name: "mk-XX"
data_files:
- split: train
path: "data/mk-XX/*.parquet"
- config_name: "ml-CO"
data_files:
- split: train
path: "data/ml-CO/*.parquet"
- config_name: "ml-GB"
data_files:
- split: train
path: "data/ml-GB/*.parquet"
- config_name: "ml-IN"
data_files:
- split: train
path: "data/ml-IN/*.parquet"
- config_name: "ml-IT"
data_files:
- split: train
path: "data/ml-IT/*.parquet"
- config_name: "ml-US"
data_files:
- split: train
path: "data/ml-US/*.parquet"
- config_name: "ml-VA"
data_files:
- split: train
path: "data/ml-VA/*.parquet"
- config_name: "ml-XX"
data_files:
- split: train
path: "data/ml-XX/*.parquet"
- config_name: "mn-AT"
data_files:
- split: train
path: "data/mn-AT/*.parquet"
- config_name: "mn-AU"
data_files:
- split: train
path: "data/mn-AU/*.parquet"
- config_name: "mn-BE"
data_files:
- split: train
path: "data/mn-BE/*.parquet"
- config_name: "mn-BZ"
data_files:
- split: train
path: "data/mn-BZ/*.parquet"
- config_name: "mn-CH"
data_files:
- split: train
path: "data/mn-CH/*.parquet"
- config_name: "mn-CZ"
data_files:
- split: train
path: "data/mn-CZ/*.parquet"
- config_name: "mn-DE"
data_files:
- split: train
path: "data/mn-DE/*.parquet"
- config_name: "mn-DK"
data_files:
- split: train
path: "data/mn-DK/*.parquet"
- config_name: "mn-EE"
data_files:
- split: train
path: "data/mn-EE/*.parquet"
- config_name: "mn-ES"
data_files:
- split: train
path: "data/mn-ES/*.parquet"
- config_name: "mn-EU"
data_files:
- split: train
path: "data/mn-EU/*.parquet"
- config_name: "mn-FR"
data_files:
- split: train
path: "data/mn-FR/*.parquet"
- config_name: "mn-GB"
data_files:
- split: train
path: "data/mn-GB/*.parquet"
- config_name: "mn-JP"
data_files:
- split: train
path: "data/mn-JP/*.parquet"
- config_name: "mn-KZ"
data_files:
- split: train
path: "data/mn-KZ/*.parquet"
- config_name: "mn-ME"
data_files:
- split: train
path: "data/mn-ME/*.parquet"
- config_name: "mn-MN"
data_files:
- split: train
path: "data/mn-MN/*.parquet"
- config_name: "mn-NL"
data_files:
- split: train
path: "data/mn-NL/*.parquet"
- config_name: "mn-PL"
data_files:
- split: train
path: "data/mn-PL/*.parquet"
- config_name: "mn-RU"
data_files:
- split: train
path: "data/mn-RU/*.parquet"
- config_name: "mn-TV"
data_files:
- split: train
path: "data/mn-TV/*.parquet"
- config_name: "mn-US"
data_files:
- split: train
path: "data/mn-US/*.parquet"
- config_name: "mn-XX"
data_files:
- split: train
path: "data/mn-XX/*.parquet"
- config_name: "mr-GB"
data_files:
- split: train
path: "data/mr-GB/*.parquet"
- config_name: "mr-IN"
data_files:
- split: train
path: "data/mr-IN/*.parquet"
- config_name: "mr-IT"
data_files:
- split: train
path: "data/mr-IT/*.parquet"
- config_name: "mr-US"
data_files:
- split: train
path: "data/mr-US/*.parquet"
- config_name: "mr-XX"
data_files:
- split: train
path: "data/mr-XX/*.parquet"
- config_name: "mrj-XX"
data_files:
- split: train
path: "data/mrj-XX/*.parquet"
- config_name: "ms-BN"
data_files:
- split: train
path: "data/ms-BN/*.parquet"
- config_name: "ms-ES"
data_files:
- split: train
path: "data/ms-ES/*.parquet"
- config_name: "ms-GB"
data_files:
- split: train
path: "data/ms-GB/*.parquet"
- config_name: "ms-HK"
data_files:
- split: train
path: "data/ms-HK/*.parquet"
- config_name: "ms-ID"
data_files:
- split: train
path: "data/ms-ID/*.parquet"
- config_name: "ms-MY"
data_files:
- split: train
path: "data/ms-MY/*.parquet"
- config_name: "ms-NL"
data_files:
- split: train
path: "data/ms-NL/*.parquet"
- config_name: "ms-SG"
data_files:
- split: train
path: "data/ms-SG/*.parquet"
- config_name: "ms-TV"
data_files:
- split: train
path: "data/ms-TV/*.parquet"
- config_name: "ms-US"
data_files:
- split: train
path: "data/ms-US/*.parquet"
- config_name: "ms-XX"
data_files:
- split: train
path: "data/ms-XX/*.parquet"
- config_name: "mt-DE"
data_files:
- split: train
path: "data/mt-DE/*.parquet"
- config_name: "mt-EU"
data_files:
- split: train
path: "data/mt-EU/*.parquet"
- config_name: "mt-FR"
data_files:
- split: train
path: "data/mt-FR/*.parquet"
- config_name: "mt-GB"
data_files:
- split: train
path: "data/mt-GB/*.parquet"
- config_name: "mt-MT"
data_files:
- split: train
path: "data/mt-MT/*.parquet"
- config_name: "mt-US"
data_files:
- split: train
path: "data/mt-US/*.parquet"
- config_name: "mt-XX"
data_files:
- split: train
path: "data/mt-XX/*.parquet"
- config_name: "mwl-XX"
data_files:
- split: train
path: "data/mwl-XX/*.parquet"
- config_name: "my-MM"
data_files:
- split: train
path: "data/my-MM/*.parquet"
- config_name: "my-US"
data_files:
- split: train
path: "data/my-US/*.parquet"
- config_name: "my-XX"
data_files:
- split: train
path: "data/my-XX/*.parquet"
- config_name: "mzn-XX"
data_files:
- split: train
path: "data/mzn-XX/*.parquet"
- config_name: "nah-XX"
data_files:
- split: train
path: "data/nah-XX/*.parquet"
- config_name: "nds-DE"
data_files:
- split: train
path: "data/nds-DE/*.parquet"
- config_name: "nds-XX"
data_files:
- split: train
path: "data/nds-XX/*.parquet"
- config_name: "ne-NP"
data_files:
- split: train
path: "data/ne-NP/*.parquet"
- config_name: "ne-US"
data_files:
- split: train
path: "data/ne-US/*.parquet"
- config_name: "ne-XX"
data_files:
- split: train
path: "data/ne-XX/*.parquet"
- config_name: "nl-AD"
data_files:
- split: train
path: "data/nl-AD/*.parquet"
- config_name: "nl-AE"
data_files:
- split: train
path: "data/nl-AE/*.parquet"
- config_name: "nl-AI"
data_files:
- split: train
path: "data/nl-AI/*.parquet"
- config_name: "nl-AM"
data_files:
- split: train
path: "data/nl-AM/*.parquet"
- config_name: "nl-AR"
data_files:
- split: train
path: "data/nl-AR/*.parquet"
- config_name: "nl-AS"
data_files:
- split: train
path: "data/nl-AS/*.parquet"
- config_name: "nl-AT"
data_files:
- split: train
path: "data/nl-AT/*.parquet"
- config_name: "nl-AU"
data_files:
- split: train
path: "data/nl-AU/*.parquet"
- config_name: "nl-AW"
data_files:
- split: train
path: "data/nl-AW/*.parquet"
- config_name: "nl-AZ"
data_files:
- split: train
path: "data/nl-AZ/*.parquet"
- config_name: "nl-BE"
data_files:
- split: train
path: "data/nl-BE/*.parquet"
- config_name: "nl-BG"
data_files:
- split: train
path: "data/nl-BG/*.parquet"
- config_name: "nl-BL"
data_files:
- split: train
path: "data/nl-BL/*.parquet"
- config_name: "nl-BM"
data_files:
- split: train
path: "data/nl-BM/*.parquet"
- config_name: "nl-BQ"
data_files:
- split: train
path: "data/nl-BQ/*.parquet"
- config_name: "nl-BR"
data_files:
- split: train
path: "data/nl-BR/*.parquet"
- config_name: "nl-BX"
data_files:
- split: train
path: "data/nl-BX/*.parquet"
- config_name: "nl-BZ"
data_files:
- split: train
path: "data/nl-BZ/*.parquet"
- config_name: "nl-CA"
data_files:
- split: train
path: "data/nl-CA/*.parquet"
- config_name: "nl-CC"
data_files:
- split: train
path: "data/nl-CC/*.parquet"
- config_name: "nl-CF"
data_files:
- split: train
path: "data/nl-CF/*.parquet"
- config_name: "nl-CH"
data_files:
- split: train
path: "data/nl-CH/*.parquet"
- config_name: "nl-CI"
data_files:
- split: train
path: "data/nl-CI/*.parquet"
- config_name: "nl-CL"
data_files:
- split: train
path: "data/nl-CL/*.parquet"
- config_name: "nl-CN"
data_files:
- split: train
path: "data/nl-CN/*.parquet"
- config_name: "nl-CO"
data_files:
- split: train
path: "data/nl-CO/*.parquet"
- config_name: "nl-CR"
data_files:
- split: train
path: "data/nl-CR/*.parquet"
- config_name: "nl-CW"
data_files:
- split: train
path: "data/nl-CW/*.parquet"
- config_name: "nl-CX"
data_files:
- split: train
path: "data/nl-CX/*.parquet"
- config_name: "nl-CZ"
data_files:
- split: train
path: "data/nl-CZ/*.parquet"
- config_name: "nl-DE"
data_files:
- split: train
path: "data/nl-DE/*.parquet"
- config_name: "nl-DK"
data_files:
- split: train
path: "data/nl-DK/*.parquet"
- config_name: "nl-EE"
data_files:
- split: train
path: "data/nl-EE/*.parquet"
- config_name: "nl-EN"
data_files:
- split: train
path: "data/nl-EN/*.parquet"
- config_name: "nl-ES"
data_files:
- split: train
path: "data/nl-ES/*.parquet"
- config_name: "nl-EU"
data_files:
- split: train
path: "data/nl-EU/*.parquet"
- config_name: "nl-FI"
data_files:
- split: train
path: "data/nl-FI/*.parquet"
- config_name: "nl-FM"
data_files:
- split: train
path: "data/nl-FM/*.parquet"
- config_name: "nl-FR"
data_files:
- split: train
path: "data/nl-FR/*.parquet"
- config_name: "nl-GA"
data_files:
- split: train
path: "data/nl-GA/*.parquet"
- config_name: "nl-GB"
data_files:
- split: train
path: "data/nl-GB/*.parquet"
- config_name: "nl-GQ"
data_files:
- split: train
path: "data/nl-GQ/*.parquet"
- config_name: "nl-GR"
data_files:
- split: train
path: "data/nl-GR/*.parquet"
- config_name: "nl-GX"
data_files:
- split: train
path: "data/nl-GX/*.parquet"
- config_name: "nl-HK"
data_files:
- split: train
path: "data/nl-HK/*.parquet"
- config_name: "nl-HR"
data_files:
- split: train
path: "data/nl-HR/*.parquet"
- config_name: "nl-HU"
data_files:
- split: train
path: "data/nl-HU/*.parquet"
- config_name: "nl-ID"
data_files:
- split: train
path: "data/nl-ID/*.parquet"
- config_name: "nl-IE"
data_files:
- split: train
path: "data/nl-IE/*.parquet"
- config_name: "nl-IL"
data_files:
- split: train
path: "data/nl-IL/*.parquet"
- config_name: "nl-IM"
data_files:
- split: train
path: "data/nl-IM/*.parquet"
- config_name: "nl-IN"
data_files:
- split: train
path: "data/nl-IN/*.parquet"
- config_name: "nl-IO"
data_files:
- split: train
path: "data/nl-IO/*.parquet"
- config_name: "nl-IR"
data_files:
- split: train
path: "data/nl-IR/*.parquet"
- config_name: "nl-IS"
data_files:
- split: train
path: "data/nl-IS/*.parquet"
- config_name: "nl-IT"
data_files:
- split: train
path: "data/nl-IT/*.parquet"
- config_name: "nl-JE"
data_files:
- split: train
path: "data/nl-JE/*.parquet"
- config_name: "nl-JP"
data_files:
- split: train
path: "data/nl-JP/*.parquet"
- config_name: "nl-KR"
data_files:
- split: train
path: "data/nl-KR/*.parquet"
- config_name: "nl-KW"
data_files:
- split: train
path: "data/nl-KW/*.parquet"
- config_name: "nl-LA"
data_files:
- split: train
path: "data/nl-LA/*.parquet"
- config_name: "nl-LI"
data_files:
- split: train
path: "data/nl-LI/*.parquet"
- config_name: "nl-LT"
data_files:
- split: train
path: "data/nl-LT/*.parquet"
- config_name: "nl-LU"
data_files:
- split: train
path: "data/nl-LU/*.parquet"
- config_name: "nl-LV"
data_files:
- split: train
path: "data/nl-LV/*.parquet"
- config_name: "nl-LY"
data_files:
- split: train
path: "data/nl-LY/*.parquet"
- config_name: "nl-MA"
data_files:
- split: train
path: "data/nl-MA/*.parquet"
- config_name: "nl-ME"
data_files:
- split: train
path: "data/nl-ME/*.parquet"
- config_name: "nl-ML"
data_files:
- split: train
path: "data/nl-ML/*.parquet"
- config_name: "nl-MS"
data_files:
- split: train
path: "data/nl-MS/*.parquet"
- config_name: "nl-MU"
data_files:
- split: train
path: "data/nl-MU/*.parquet"
- config_name: "nl-MX"
data_files:
- split: train
path: "data/nl-MX/*.parquet"
- config_name: "nl-MY"
data_files:
- split: train
path: "data/nl-MY/*.parquet"
- config_name: "nl-NL"
data_files:
- split: train
path: "data/nl-NL/*.parquet"
- config_name: "nl-NO"
data_files:
- split: train
path: "data/nl-NO/*.parquet"
- config_name: "nl-NU"
data_files:
- split: train
path: "data/nl-NU/*.parquet"
- config_name: "nl-PH"
data_files:
- split: train
path: "data/nl-PH/*.parquet"
- config_name: "nl-PL"
data_files:
- split: train
path: "data/nl-PL/*.parquet"
- config_name: "nl-PT"
data_files:
- split: train
path: "data/nl-PT/*.parquet"
- config_name: "nl-PW"
data_files:
- split: train
path: "data/nl-PW/*.parquet"
- config_name: "nl-RE"
data_files:
- split: train
path: "data/nl-RE/*.parquet"
- config_name: "nl-RO"
data_files:
- split: train
path: "data/nl-RO/*.parquet"
- config_name: "nl-RS"
data_files:
- split: train
path: "data/nl-RS/*.parquet"
- config_name: "nl-RU"
data_files:
- split: train
path: "data/nl-RU/*.parquet"
- config_name: "nl-RW"
data_files:
- split: train
path: "data/nl-RW/*.parquet"
- config_name: "nl-SA"
data_files:
- split: train
path: "data/nl-SA/*.parquet"
- config_name: "nl-SC"
data_files:
- split: train
path: "data/nl-SC/*.parquet"
- config_name: "nl-SE"
data_files:
- split: train
path: "data/nl-SE/*.parquet"
- config_name: "nl-SG"
data_files:
- split: train
path: "data/nl-SG/*.parquet"
- config_name: "nl-SH"
data_files:
- split: train
path: "data/nl-SH/*.parquet"
- config_name: "nl-SI"
data_files:
- split: train
path: "data/nl-SI/*.parquet"
- config_name: "nl-SK"
data_files:
- split: train
path: "data/nl-SK/*.parquet"
- config_name: "nl-SN"
data_files:
- split: train
path: "data/nl-SN/*.parquet"
- config_name: "nl-SR"
data_files:
- split: train
path: "data/nl-SR/*.parquet"
- config_name: "nl-ST"
data_files:
- split: train
path: "data/nl-ST/*.parquet"
- config_name: "nl-SX"
data_files:
- split: train
path: "data/nl-SX/*.parquet"
- config_name: "nl-TH"
data_files:
- split: train
path: "data/nl-TH/*.parquet"
- config_name: "nl-TK"
data_files:
- split: train
path: "data/nl-TK/*.parquet"
- config_name: "nl-TO"
data_files:
- split: train
path: "data/nl-TO/*.parquet"
- config_name: "nl-TR"
data_files:
- split: train
path: "data/nl-TR/*.parquet"
- config_name: "nl-TT"
data_files:
- split: train
path: "data/nl-TT/*.parquet"
- config_name: "nl-TV"
data_files:
- split: train
path: "data/nl-TV/*.parquet"
- config_name: "nl-TW"
data_files:
- split: train
path: "data/nl-TW/*.parquet"
- config_name: "nl-UA"
data_files:
- split: train
path: "data/nl-UA/*.parquet"
- config_name: "nl-UK"
data_files:
- split: train
path: "data/nl-UK/*.parquet"
- config_name: "nl-US"
data_files:
- split: train
path: "data/nl-US/*.parquet"
- config_name: "nl-VG"
data_files:
- split: train
path: "data/nl-VG/*.parquet"
- config_name: "nl-VN"
data_files:
- split: train
path: "data/nl-VN/*.parquet"
- config_name: "nl-VU"
data_files:
- split: train
path: "data/nl-VU/*.parquet"
- config_name: "nl-WS"
data_files:
- split: train
path: "data/nl-WS/*.parquet"
- config_name: "nl-XX"
data_files:
- split: train
path: "data/nl-XX/*.parquet"
- config_name: "nl-ZA"
data_files:
- split: train
path: "data/nl-ZA/*.parquet"
- config_name: "nl-ZM"
data_files:
- split: train
path: "data/nl-ZM/*.parquet"
- config_name: "nn-GB"
data_files:
- split: train
path: "data/nn-GB/*.parquet"
- config_name: "nn-LY"
data_files:
- split: train
path: "data/nn-LY/*.parquet"
- config_name: "nn-ME"
data_files:
- split: train
path: "data/nn-ME/*.parquet"
- config_name: "nn-NN"
data_files:
- split: train
path: "data/nn-NN/*.parquet"
- config_name: "nn-NO"
data_files:
- split: train
path: "data/nn-NO/*.parquet"
- config_name: "nn-US"
data_files:
- split: train
path: "data/nn-US/*.parquet"
- config_name: "nn-XX"
data_files:
- split: train
path: "data/nn-XX/*.parquet"
- config_name: "no-AI"
data_files:
- split: train
path: "data/no-AI/*.parquet"
- config_name: "no-AS"
data_files:
- split: train
path: "data/no-AS/*.parquet"
- config_name: "no-AT"
data_files:
- split: train
path: "data/no-AT/*.parquet"
- config_name: "no-AU"
data_files:
- split: train
path: "data/no-AU/*.parquet"
- config_name: "no-BE"
data_files:
- split: train
path: "data/no-BE/*.parquet"
- config_name: "no-BG"
data_files:
- split: train
path: "data/no-BG/*.parquet"
- config_name: "no-BM"
data_files:
- split: train
path: "data/no-BM/*.parquet"
- config_name: "no-BN"
data_files:
- split: train
path: "data/no-BN/*.parquet"
- config_name: "no-BR"
data_files:
- split: train
path: "data/no-BR/*.parquet"
- config_name: "no-BY"
data_files:
- split: train
path: "data/no-BY/*.parquet"
- config_name: "no-CA"
data_files:
- split: train
path: "data/no-CA/*.parquet"
- config_name: "no-CC"
data_files:
- split: train
path: "data/no-CC/*.parquet"
- config_name: "no-CH"
data_files:
- split: train
path: "data/no-CH/*.parquet"
- config_name: "no-CL"
data_files:
- split: train
path: "data/no-CL/*.parquet"
- config_name: "no-CN"
data_files:
- split: train
path: "data/no-CN/*.parquet"
- config_name: "no-CO"
data_files:
- split: train
path: "data/no-CO/*.parquet"
- config_name: "no-CZ"
data_files:
- split: train
path: "data/no-CZ/*.parquet"
- config_name: "no-DE"
data_files:
- split: train
path: "data/no-DE/*.parquet"
- config_name: "no-DK"
data_files:
- split: train
path: "data/no-DK/*.parquet"
- config_name: "no-EC"
data_files:
- split: train
path: "data/no-EC/*.parquet"
- config_name: "no-EN"
data_files:
- split: train
path: "data/no-EN/*.parquet"
- config_name: "no-ES"
data_files:
- split: train
path: "data/no-ES/*.parquet"
- config_name: "no-EU"
data_files:
- split: train
path: "data/no-EU/*.parquet"
- config_name: "no-FI"
data_files:
- split: train
path: "data/no-FI/*.parquet"
- config_name: "no-FM"
data_files:
- split: train
path: "data/no-FM/*.parquet"
- config_name: "no-FO"
data_files:
- split: train
path: "data/no-FO/*.parquet"
- config_name: "no-FR"
data_files:
- split: train
path: "data/no-FR/*.parquet"
- config_name: "no-GB"
data_files:
- split: train
path: "data/no-GB/*.parquet"
- config_name: "no-GR"
data_files:
- split: train
path: "data/no-GR/*.parquet"
- config_name: "no-HR"
data_files:
- split: train
path: "data/no-HR/*.parquet"
- config_name: "no-ID"
data_files:
- split: train
path: "data/no-ID/*.parquet"
- config_name: "no-IL"
data_files:
- split: train
path: "data/no-IL/*.parquet"
- config_name: "no-IN"
data_files:
- split: train
path: "data/no-IN/*.parquet"
- config_name: "no-IO"
data_files:
- split: train
path: "data/no-IO/*.parquet"
- config_name: "no-IR"
data_files:
- split: train
path: "data/no-IR/*.parquet"
- config_name: "no-IS"
data_files:
- split: train
path: "data/no-IS/*.parquet"
- config_name: "no-IT"
data_files:
- split: train
path: "data/no-IT/*.parquet"
- config_name: "no-JP"
data_files:
- split: train
path: "data/no-JP/*.parquet"
- config_name: "no-KR"
data_files:
- split: train
path: "data/no-KR/*.parquet"
- config_name: "no-LT"
data_files:
- split: train
path: "data/no-LT/*.parquet"
- config_name: "no-LY"
data_files:
- split: train
path: "data/no-LY/*.parquet"
- config_name: "no-MA"
data_files:
- split: train
path: "data/no-MA/*.parquet"
- config_name: "no-ME"
data_files:
- split: train
path: "data/no-ME/*.parquet"
- config_name: "no-ML"
data_files:
- split: train
path: "data/no-ML/*.parquet"
- config_name: "no-MX"
data_files:
- split: train
path: "data/no-MX/*.parquet"
- config_name: "no-NB"
data_files:
- split: train
path: "data/no-NB/*.parquet"
- config_name: "no-NL"
data_files:
- split: train
path: "data/no-NL/*.parquet"
- config_name: "no-NN"
data_files:
- split: train
path: "data/no-NN/*.parquet"
- config_name: "no-NO"
data_files:
- split: train
path: "data/no-NO/*.parquet"
- config_name: "no-NU"
data_files:
- split: train
path: "data/no-NU/*.parquet"
- config_name: "no-NZ"
data_files:
- split: train
path: "data/no-NZ/*.parquet"
- config_name: "no-PE"
data_files:
- split: train
path: "data/no-PE/*.parquet"
- config_name: "no-PL"
data_files:
- split: train
path: "data/no-PL/*.parquet"
- config_name: "no-PT"
data_files:
- split: train
path: "data/no-PT/*.parquet"
- config_name: "no-PW"
data_files:
- split: train
path: "data/no-PW/*.parquet"
- config_name: "no-PY"
data_files:
- split: train
path: "data/no-PY/*.parquet"
- config_name: "no-RO"
data_files:
- split: train
path: "data/no-RO/*.parquet"
- config_name: "no-RS"
data_files:
- split: train
path: "data/no-RS/*.parquet"
- config_name: "no-RU"
data_files:
- split: train
path: "data/no-RU/*.parquet"
- config_name: "no-SE"
data_files:
- split: train
path: "data/no-SE/*.parquet"
- config_name: "no-SH"
data_files:
- split: train
path: "data/no-SH/*.parquet"
- config_name: "no-SK"
data_files:
- split: train
path: "data/no-SK/*.parquet"
- config_name: "no-TK"
data_files:
- split: train
path: "data/no-TK/*.parquet"
- config_name: "no-TR"
data_files:
- split: train
path: "data/no-TR/*.parquet"
- config_name: "no-TV"
data_files:
- split: train
path: "data/no-TV/*.parquet"
- config_name: "no-TW"
data_files:
- split: train
path: "data/no-TW/*.parquet"
- config_name: "no-UA"
data_files:
- split: train
path: "data/no-UA/*.parquet"
- config_name: "no-UK"
data_files:
- split: train
path: "data/no-UK/*.parquet"
- config_name: "no-US"
data_files:
- split: train
path: "data/no-US/*.parquet"
- config_name: "no-VA"
data_files:
- split: train
path: "data/no-VA/*.parquet"
- config_name: "no-VN"
data_files:
- split: train
path: "data/no-VN/*.parquet"
- config_name: "no-XX"
data_files:
- split: train
path: "data/no-XX/*.parquet"
- config_name: "no-ZA"
data_files:
- split: train
path: "data/no-ZA/*.parquet"
- config_name: "oc-EU"
data_files:
- split: train
path: "data/oc-EU/*.parquet"
- config_name: "oc-FR"
data_files:
- split: train
path: "data/oc-FR/*.parquet"
- config_name: "oc-GB"
data_files:
- split: train
path: "data/oc-GB/*.parquet"
- config_name: "oc-XX"
data_files:
- split: train
path: "data/oc-XX/*.parquet"
- config_name: "or-IN"
data_files:
- split: train
path: "data/or-IN/*.parquet"
- config_name: "or-US"
data_files:
- split: train
path: "data/or-US/*.parquet"
- config_name: "or-XX"
data_files:
- split: train
path: "data/or-XX/*.parquet"
- config_name: "os-EU"
data_files:
- split: train
path: "data/os-EU/*.parquet"
- config_name: "os-RU"
data_files:
- split: train
path: "data/os-RU/*.parquet"
- config_name: "os-TV"
data_files:
- split: train
path: "data/os-TV/*.parquet"
- config_name: "os-US"
data_files:
- split: train
path: "data/os-US/*.parquet"
- config_name: "os-XX"
data_files:
- split: train
path: "data/os-XX/*.parquet"
- config_name: "pa-GB"
data_files:
- split: train
path: "data/pa-GB/*.parquet"
- config_name: "pa-IN"
data_files:
- split: train
path: "data/pa-IN/*.parquet"
- config_name: "pa-US"
data_files:
- split: train
path: "data/pa-US/*.parquet"
- config_name: "pa-XX"
data_files:
- split: train
path: "data/pa-XX/*.parquet"
- config_name: "pl-AA"
data_files:
- split: train
path: "data/pl-AA/*.parquet"
- config_name: "pl-AI"
data_files:
- split: train
path: "data/pl-AI/*.parquet"
- config_name: "pl-AL"
data_files:
- split: train
path: "data/pl-AL/*.parquet"
- config_name: "pl-AM"
data_files:
- split: train
path: "data/pl-AM/*.parquet"
- config_name: "pl-AR"
data_files:
- split: train
path: "data/pl-AR/*.parquet"
- config_name: "pl-AT"
data_files:
- split: train
path: "data/pl-AT/*.parquet"
- config_name: "pl-AU"
data_files:
- split: train
path: "data/pl-AU/*.parquet"
- config_name: "pl-BA"
data_files:
- split: train
path: "data/pl-BA/*.parquet"
- config_name: "pl-BE"
data_files:
- split: train
path: "data/pl-BE/*.parquet"
- config_name: "pl-BG"
data_files:
- split: train
path: "data/pl-BG/*.parquet"
- config_name: "pl-BM"
data_files:
- split: train
path: "data/pl-BM/*.parquet"
- config_name: "pl-BR"
data_files:
- split: train
path: "data/pl-BR/*.parquet"
- config_name: "pl-BY"
data_files:
- split: train
path: "data/pl-BY/*.parquet"
- config_name: "pl-CA"
data_files:
- split: train
path: "data/pl-CA/*.parquet"
- config_name: "pl-CC"
data_files:
- split: train
path: "data/pl-CC/*.parquet"
- config_name: "pl-CD"
data_files:
- split: train
path: "data/pl-CD/*.parquet"
- config_name: "pl-CF"
data_files:
- split: train
path: "data/pl-CF/*.parquet"
- config_name: "pl-CH"
data_files:
- split: train
path: "data/pl-CH/*.parquet"
- config_name: "pl-CL"
data_files:
- split: train
path: "data/pl-CL/*.parquet"
- config_name: "pl-CN"
data_files:
- split: train
path: "data/pl-CN/*.parquet"
- config_name: "pl-CO"
data_files:
- split: train
path: "data/pl-CO/*.parquet"
- config_name: "pl-CY"
data_files:
- split: train
path: "data/pl-CY/*.parquet"
- config_name: "pl-CZ"
data_files:
- split: train
path: "data/pl-CZ/*.parquet"
- config_name: "pl-DE"
data_files:
- split: train
path: "data/pl-DE/*.parquet"
- config_name: "pl-DK"
data_files:
- split: train
path: "data/pl-DK/*.parquet"
- config_name: "pl-DO"
data_files:
- split: train
path: "data/pl-DO/*.parquet"
- config_name: "pl-EC"
data_files:
- split: train
path: "data/pl-EC/*.parquet"
- config_name: "pl-EE"
data_files:
- split: train
path: "data/pl-EE/*.parquet"
- config_name: "pl-EG"
data_files:
- split: train
path: "data/pl-EG/*.parquet"
- config_name: "pl-EN"
data_files:
- split: train
path: "data/pl-EN/*.parquet"
- config_name: "pl-ES"
data_files:
- split: train
path: "data/pl-ES/*.parquet"
- config_name: "pl-EU"
data_files:
- split: train
path: "data/pl-EU/*.parquet"
- config_name: "pl-FI"
data_files:
- split: train
path: "data/pl-FI/*.parquet"
- config_name: "pl-FM"
data_files:
- split: train
path: "data/pl-FM/*.parquet"
- config_name: "pl-FR"
data_files:
- split: train
path: "data/pl-FR/*.parquet"
- config_name: "pl-GA"
data_files:
- split: train
path: "data/pl-GA/*.parquet"
- config_name: "pl-GB"
data_files:
- split: train
path: "data/pl-GB/*.parquet"
- config_name: "pl-GD"
data_files:
- split: train
path: "data/pl-GD/*.parquet"
- config_name: "pl-GE"
data_files:
- split: train
path: "data/pl-GE/*.parquet"
- config_name: "pl-GP"
data_files:
- split: train
path: "data/pl-GP/*.parquet"
- config_name: "pl-GR"
data_files:
- split: train
path: "data/pl-GR/*.parquet"
- config_name: "pl-HK"
data_files:
- split: train
path: "data/pl-HK/*.parquet"
- config_name: "pl-HR"
data_files:
- split: train
path: "data/pl-HR/*.parquet"
- config_name: "pl-HT"
data_files:
- split: train
path: "data/pl-HT/*.parquet"
- config_name: "pl-HU"
data_files:
- split: train
path: "data/pl-HU/*.parquet"
- config_name: "pl-ID"
data_files:
- split: train
path: "data/pl-ID/*.parquet"
- config_name: "pl-IE"
data_files:
- split: train
path: "data/pl-IE/*.parquet"
- config_name: "pl-IL"
data_files:
- split: train
path: "data/pl-IL/*.parquet"
- config_name: "pl-IN"
data_files:
- split: train
path: "data/pl-IN/*.parquet"
- config_name: "pl-IO"
data_files:
- split: train
path: "data/pl-IO/*.parquet"
- config_name: "pl-IR"
data_files:
- split: train
path: "data/pl-IR/*.parquet"
- config_name: "pl-IS"
data_files:
- split: train
path: "data/pl-IS/*.parquet"
- config_name: "pl-IT"
data_files:
- split: train
path: "data/pl-IT/*.parquet"
- config_name: "pl-JP"
data_files:
- split: train
path: "data/pl-JP/*.parquet"
- config_name: "pl-KE"
data_files:
- split: train
path: "data/pl-KE/*.parquet"
- config_name: "pl-KR"
data_files:
- split: train
path: "data/pl-KR/*.parquet"
- config_name: "pl-LA"
data_files:
- split: train
path: "data/pl-LA/*.parquet"
- config_name: "pl-LT"
data_files:
- split: train
path: "data/pl-LT/*.parquet"
- config_name: "pl-LU"
data_files:
- split: train
path: "data/pl-LU/*.parquet"
- config_name: "pl-LV"
data_files:
- split: train
path: "data/pl-LV/*.parquet"
- config_name: "pl-ME"
data_files:
- split: train
path: "data/pl-ME/*.parquet"
- config_name: "pl-ML"
data_files:
- split: train
path: "data/pl-ML/*.parquet"
- config_name: "pl-MX"
data_files:
- split: train
path: "data/pl-MX/*.parquet"
- config_name: "pl-MY"
data_files:
- split: train
path: "data/pl-MY/*.parquet"
- config_name: "pl-NF"
data_files:
- split: train
path: "data/pl-NF/*.parquet"
- config_name: "pl-NL"
data_files:
- split: train
path: "data/pl-NL/*.parquet"
- config_name: "pl-NO"
data_files:
- split: train
path: "data/pl-NO/*.parquet"
- config_name: "pl-NZ"
data_files:
- split: train
path: "data/pl-NZ/*.parquet"
- config_name: "pl-PE"
data_files:
- split: train
path: "data/pl-PE/*.parquet"
- config_name: "pl-PH"
data_files:
- split: train
path: "data/pl-PH/*.parquet"
- config_name: "pl-PK"
data_files:
- split: train
path: "data/pl-PK/*.parquet"
- config_name: "pl-PL"
data_files:
- split: train
path: "data/pl-PL/*.parquet"
- config_name: "pl-PO"
data_files:
- split: train
path: "data/pl-PO/*.parquet"
- config_name: "pl-PT"
data_files:
- split: train
path: "data/pl-PT/*.parquet"
- config_name: "pl-PW"
data_files:
- split: train
path: "data/pl-PW/*.parquet"
- config_name: "pl-RO"
data_files:
- split: train
path: "data/pl-RO/*.parquet"
- config_name: "pl-RS"
data_files:
- split: train
path: "data/pl-RS/*.parquet"
- config_name: "pl-RU"
data_files:
- split: train
path: "data/pl-RU/*.parquet"
- config_name: "pl-SA"
data_files:
- split: train
path: "data/pl-SA/*.parquet"
- config_name: "pl-SE"
data_files:
- split: train
path: "data/pl-SE/*.parquet"
- config_name: "pl-SH"
data_files:
- split: train
path: "data/pl-SH/*.parquet"
- config_name: "pl-SI"
data_files:
- split: train
path: "data/pl-SI/*.parquet"
- config_name: "pl-SK"
data_files:
- split: train
path: "data/pl-SK/*.parquet"
- config_name: "pl-TK"
data_files:
- split: train
path: "data/pl-TK/*.parquet"
- config_name: "pl-TL"
data_files:
- split: train
path: "data/pl-TL/*.parquet"
- config_name: "pl-TO"
data_files:
- split: train
path: "data/pl-TO/*.parquet"
- config_name: "pl-TR"
data_files:
- split: train
path: "data/pl-TR/*.parquet"
- config_name: "pl-TV"
data_files:
- split: train
path: "data/pl-TV/*.parquet"
- config_name: "pl-TW"
data_files:
- split: train
path: "data/pl-TW/*.parquet"
- config_name: "pl-UA"
data_files:
- split: train
path: "data/pl-UA/*.parquet"
- config_name: "pl-UK"
data_files:
- split: train
path: "data/pl-UK/*.parquet"
- config_name: "pl-US"
data_files:
- split: train
path: "data/pl-US/*.parquet"
- config_name: "pl-VA"
data_files:
- split: train
path: "data/pl-VA/*.parquet"
- config_name: "pl-VN"
data_files:
- split: train
path: "data/pl-VN/*.parquet"
- config_name: "pl-WS"
data_files:
- split: train
path: "data/pl-WS/*.parquet"
- config_name: "pl-XX"
data_files:
- split: train
path: "data/pl-XX/*.parquet"
- config_name: "pl-YT"
data_files:
- split: train
path: "data/pl-YT/*.parquet"
- config_name: "pl-ZA"
data_files:
- split: train
path: "data/pl-ZA/*.parquet"
- config_name: "pms-GB"
data_files:
- split: train
path: "data/pms-GB/*.parquet"
- config_name: "pms-XX"
data_files:
- split: train
path: "data/pms-XX/*.parquet"
- config_name: "pnb-PK"
data_files:
- split: train
path: "data/pnb-PK/*.parquet"
- config_name: "pnb-US"
data_files:
- split: train
path: "data/pnb-US/*.parquet"
- config_name: "pnb-XX"
data_files:
- split: train
path: "data/pnb-XX/*.parquet"
- config_name: "ps-AF"
data_files:
- split: train
path: "data/ps-AF/*.parquet"
- config_name: "ps-CA"
data_files:
- split: train
path: "data/ps-CA/*.parquet"
- config_name: "ps-CN"
data_files:
- split: train
path: "data/ps-CN/*.parquet"
- config_name: "ps-CO"
data_files:
- split: train
path: "data/ps-CO/*.parquet"
- config_name: "ps-DE"
data_files:
- split: train
path: "data/ps-DE/*.parquet"
- config_name: "ps-FR"
data_files:
- split: train
path: "data/ps-FR/*.parquet"
- config_name: "ps-GB"
data_files:
- split: train
path: "data/ps-GB/*.parquet"
- config_name: "ps-IR"
data_files:
- split: train
path: "data/ps-IR/*.parquet"
- config_name: "ps-KZ"
data_files:
- split: train
path: "data/ps-KZ/*.parquet"
- config_name: "ps-NL"
data_files:
- split: train
path: "data/ps-NL/*.parquet"
- config_name: "ps-PA"
data_files:
- split: train
path: "data/ps-PA/*.parquet"
- config_name: "ps-PK"
data_files:
- split: train
path: "data/ps-PK/*.parquet"
- config_name: "ps-PS"
data_files:
- split: train
path: "data/ps-PS/*.parquet"
- config_name: "ps-TR"
data_files:
- split: train
path: "data/ps-TR/*.parquet"
- config_name: "ps-TV"
data_files:
- split: train
path: "data/ps-TV/*.parquet"
- config_name: "ps-US"
data_files:
- split: train
path: "data/ps-US/*.parquet"
- config_name: "ps-UZ"
data_files:
- split: train
path: "data/ps-UZ/*.parquet"
- config_name: "ps-XX"
data_files:
- split: train
path: "data/ps-XX/*.parquet"
- config_name: "pt-AE"
data_files:
- split: train
path: "data/pt-AE/*.parquet"
- config_name: "pt-AG"
data_files:
- split: train
path: "data/pt-AG/*.parquet"
- config_name: "pt-AI"
data_files:
- split: train
path: "data/pt-AI/*.parquet"
- config_name: "pt-AL"
data_files:
- split: train
path: "data/pt-AL/*.parquet"
- config_name: "pt-AM"
data_files:
- split: train
path: "data/pt-AM/*.parquet"
- config_name: "pt-AO"
data_files:
- split: train
path: "data/pt-AO/*.parquet"
- config_name: "pt-AR"
data_files:
- split: train
path: "data/pt-AR/*.parquet"
- config_name: "pt-AT"
data_files:
- split: train
path: "data/pt-AT/*.parquet"
- config_name: "pt-AU"
data_files:
- split: train
path: "data/pt-AU/*.parquet"
- config_name: "pt-BA"
data_files:
- split: train
path: "data/pt-BA/*.parquet"
- config_name: "pt-BD"
data_files:
- split: train
path: "data/pt-BD/*.parquet"
- config_name: "pt-BE"
data_files:
- split: train
path: "data/pt-BE/*.parquet"
- config_name: "pt-BG"
data_files:
- split: train
path: "data/pt-BG/*.parquet"
- config_name: "pt-BM"
data_files:
- split: train
path: "data/pt-BM/*.parquet"
- config_name: "pt-BO"
data_files:
- split: train
path: "data/pt-BO/*.parquet"
- config_name: "pt-BR"
data_files:
- split: train
path: "data/pt-BR/*.parquet"
- config_name: "pt-BT"
data_files:
- split: train
path: "data/pt-BT/*.parquet"
- config_name: "pt-BY"
data_files:
- split: train
path: "data/pt-BY/*.parquet"
- config_name: "pt-BZ"
data_files:
- split: train
path: "data/pt-BZ/*.parquet"
- config_name: "pt-CA"
data_files:
- split: train
path: "data/pt-CA/*.parquet"
- config_name: "pt-CC"
data_files:
- split: train
path: "data/pt-CC/*.parquet"
- config_name: "pt-CF"
data_files:
- split: train
path: "data/pt-CF/*.parquet"
- config_name: "pt-CH"
data_files:
- split: train
path: "data/pt-CH/*.parquet"
- config_name: "pt-CL"
data_files:
- split: train
path: "data/pt-CL/*.parquet"
- config_name: "pt-CN"
data_files:
- split: train
path: "data/pt-CN/*.parquet"
- config_name: "pt-CO"
data_files:
- split: train
path: "data/pt-CO/*.parquet"
- config_name: "pt-CR"
data_files:
- split: train
path: "data/pt-CR/*.parquet"
- config_name: "pt-CU"
data_files:
- split: train
path: "data/pt-CU/*.parquet"
- config_name: "pt-CV"
data_files:
- split: train
path: "data/pt-CV/*.parquet"
- config_name: "pt-CY"
data_files:
- split: train
path: "data/pt-CY/*.parquet"
- config_name: "pt-CZ"
data_files:
- split: train
path: "data/pt-CZ/*.parquet"
- config_name: "pt-DE"
data_files:
- split: train
path: "data/pt-DE/*.parquet"
- config_name: "pt-DJ"
data_files:
- split: train
path: "data/pt-DJ/*.parquet"
- config_name: "pt-DK"
data_files:
- split: train
path: "data/pt-DK/*.parquet"
- config_name: "pt-DO"
data_files:
- split: train
path: "data/pt-DO/*.parquet"
- config_name: "pt-EN"
data_files:
- split: train
path: "data/pt-EN/*.parquet"
- config_name: "pt-ES"
data_files:
- split: train
path: "data/pt-ES/*.parquet"
- config_name: "pt-EU"
data_files:
- split: train
path: "data/pt-EU/*.parquet"
- config_name: "pt-FI"
data_files:
- split: train
path: "data/pt-FI/*.parquet"
- config_name: "pt-FM"
data_files:
- split: train
path: "data/pt-FM/*.parquet"
- config_name: "pt-FO"
data_files:
- split: train
path: "data/pt-FO/*.parquet"
- config_name: "pt-FR"
data_files:
- split: train
path: "data/pt-FR/*.parquet"
- config_name: "pt-GA"
data_files:
- split: train
path: "data/pt-GA/*.parquet"
- config_name: "pt-GB"
data_files:
- split: train
path: "data/pt-GB/*.parquet"
- config_name: "pt-GE"
data_files:
- split: train
path: "data/pt-GE/*.parquet"
- config_name: "pt-GG"
data_files:
- split: train
path: "data/pt-GG/*.parquet"
- config_name: "pt-GL"
data_files:
- split: train
path: "data/pt-GL/*.parquet"
- config_name: "pt-GQ"
data_files:
- split: train
path: "data/pt-GQ/*.parquet"
- config_name: "pt-GR"
data_files:
- split: train
path: "data/pt-GR/*.parquet"
- config_name: "pt-GW"
data_files:
- split: train
path: "data/pt-GW/*.parquet"
- config_name: "pt-GX"
data_files:
- split: train
path: "data/pt-GX/*.parquet"
- config_name: "pt-GY"
data_files:
- split: train
path: "data/pt-GY/*.parquet"
- config_name: "pt-GZ"
data_files:
- split: train
path: "data/pt-GZ/*.parquet"
- config_name: "pt-HK"
data_files:
- split: train
path: "data/pt-HK/*.parquet"
- config_name: "pt-HU"
data_files:
- split: train
path: "data/pt-HU/*.parquet"
- config_name: "pt-ID"
data_files:
- split: train
path: "data/pt-ID/*.parquet"
- config_name: "pt-IE"
data_files:
- split: train
path: "data/pt-IE/*.parquet"
- config_name: "pt-IL"
data_files:
- split: train
path: "data/pt-IL/*.parquet"
- config_name: "pt-IM"
data_files:
- split: train
path: "data/pt-IM/*.parquet"
- config_name: "pt-IN"
data_files:
- split: train
path: "data/pt-IN/*.parquet"
- config_name: "pt-IO"
data_files:
- split: train
path: "data/pt-IO/*.parquet"
- config_name: "pt-IR"
data_files:
- split: train
path: "data/pt-IR/*.parquet"
- config_name: "pt-IS"
data_files:
- split: train
path: "data/pt-IS/*.parquet"
- config_name: "pt-IT"
data_files:
- split: train
path: "data/pt-IT/*.parquet"
- config_name: "pt-JM"
data_files:
- split: train
path: "data/pt-JM/*.parquet"
- config_name: "pt-JP"
data_files:
- split: train
path: "data/pt-JP/*.parquet"
- config_name: "pt-KE"
data_files:
- split: train
path: "data/pt-KE/*.parquet"
- config_name: "pt-KR"
data_files:
- split: train
path: "data/pt-KR/*.parquet"
- config_name: "pt-LA"
data_files:
- split: train
path: "data/pt-LA/*.parquet"
- config_name: "pt-LI"
data_files:
- split: train
path: "data/pt-LI/*.parquet"
- config_name: "pt-LT"
data_files:
- split: train
path: "data/pt-LT/*.parquet"
- config_name: "pt-LU"
data_files:
- split: train
path: "data/pt-LU/*.parquet"
- config_name: "pt-MA"
data_files:
- split: train
path: "data/pt-MA/*.parquet"
- config_name: "pt-MC"
data_files:
- split: train
path: "data/pt-MC/*.parquet"
- config_name: "pt-ME"
data_files:
- split: train
path: "data/pt-ME/*.parquet"
- config_name: "pt-ML"
data_files:
- split: train
path: "data/pt-ML/*.parquet"
- config_name: "pt-MN"
data_files:
- split: train
path: "data/pt-MN/*.parquet"
- config_name: "pt-MO"
data_files:
- split: train
path: "data/pt-MO/*.parquet"
- config_name: "pt-MP"
data_files:
- split: train
path: "data/pt-MP/*.parquet"
- config_name: "pt-MS"
data_files:
- split: train
path: "data/pt-MS/*.parquet"
- config_name: "pt-MX"
data_files:
- split: train
path: "data/pt-MX/*.parquet"
- config_name: "pt-MY"
data_files:
- split: train
path: "data/pt-MY/*.parquet"
- config_name: "pt-MZ"
data_files:
- split: train
path: "data/pt-MZ/*.parquet"
- config_name: "pt-NL"
data_files:
- split: train
path: "data/pt-NL/*.parquet"
- config_name: "pt-NO"
data_files:
- split: train
path: "data/pt-NO/*.parquet"
- config_name: "pt-NZ"
data_files:
- split: train
path: "data/pt-NZ/*.parquet"
- config_name: "pt-PA"
data_files:
- split: train
path: "data/pt-PA/*.parquet"
- config_name: "pt-PE"
data_files:
- split: train
path: "data/pt-PE/*.parquet"
- config_name: "pt-PH"
data_files:
- split: train
path: "data/pt-PH/*.parquet"
- config_name: "pt-PL"
data_files:
- split: train
path: "data/pt-PL/*.parquet"
- config_name: "pt-PM"
data_files:
- split: train
path: "data/pt-PM/*.parquet"
- config_name: "pt-PR"
data_files:
- split: train
path: "data/pt-PR/*.parquet"
- config_name: "pt-PT"
data_files:
- split: train
path: "data/pt-PT/*.parquet"
- config_name: "pt-PW"
data_files:
- split: train
path: "data/pt-PW/*.parquet"
- config_name: "pt-PY"
data_files:
- split: train
path: "data/pt-PY/*.parquet"
- config_name: "pt-RO"
data_files:
- split: train
path: "data/pt-RO/*.parquet"
- config_name: "pt-RS"
data_files:
- split: train
path: "data/pt-RS/*.parquet"
- config_name: "pt-RU"
data_files:
- split: train
path: "data/pt-RU/*.parquet"
- config_name: "pt-SA"
data_files:
- split: train
path: "data/pt-SA/*.parquet"
- config_name: "pt-SE"
data_files:
- split: train
path: "data/pt-SE/*.parquet"
- config_name: "pt-SI"
data_files:
- split: train
path: "data/pt-SI/*.parquet"
- config_name: "pt-SK"
data_files:
- split: train
path: "data/pt-SK/*.parquet"
- config_name: "pt-SM"
data_files:
- split: train
path: "data/pt-SM/*.parquet"
- config_name: "pt-SO"
data_files:
- split: train
path: "data/pt-SO/*.parquet"
- config_name: "pt-SP"
data_files:
- split: train
path: "data/pt-SP/*.parquet"
- config_name: "pt-ST"
data_files:
- split: train
path: "data/pt-ST/*.parquet"
- config_name: "pt-TH"
data_files:
- split: train
path: "data/pt-TH/*.parquet"
- config_name: "pt-TK"
data_files:
- split: train
path: "data/pt-TK/*.parquet"
- config_name: "pt-TL"
data_files:
- split: train
path: "data/pt-TL/*.parquet"
- config_name: "pt-TO"
data_files:
- split: train
path: "data/pt-TO/*.parquet"
- config_name: "pt-TR"
data_files:
- split: train
path: "data/pt-TR/*.parquet"
- config_name: "pt-TV"
data_files:
- split: train
path: "data/pt-TV/*.parquet"
- config_name: "pt-TW"
data_files:
- split: train
path: "data/pt-TW/*.parquet"
- config_name: "pt-UA"
data_files:
- split: train
path: "data/pt-UA/*.parquet"
- config_name: "pt-UK"
data_files:
- split: train
path: "data/pt-UK/*.parquet"
- config_name: "pt-US"
data_files:
- split: train
path: "data/pt-US/*.parquet"
- config_name: "pt-UY"
data_files:
- split: train
path: "data/pt-UY/*.parquet"
- config_name: "pt-VA"
data_files:
- split: train
path: "data/pt-VA/*.parquet"
- config_name: "pt-VC"
data_files:
- split: train
path: "data/pt-VC/*.parquet"
- config_name: "pt-VN"
data_files:
- split: train
path: "data/pt-VN/*.parquet"
- config_name: "pt-VU"
data_files:
- split: train
path: "data/pt-VU/*.parquet"
- config_name: "pt-WF"
data_files:
- split: train
path: "data/pt-WF/*.parquet"
- config_name: "pt-WP"
data_files:
- split: train
path: "data/pt-WP/*.parquet"
- config_name: "pt-WS"
data_files:
- split: train
path: "data/pt-WS/*.parquet"
- config_name: "pt-XX"
data_files:
- split: train
path: "data/pt-XX/*.parquet"
- config_name: "pt-ZA"
data_files:
- split: train
path: "data/pt-ZA/*.parquet"
- config_name: "qu-XX"
data_files:
- split: train
path: "data/qu-XX/*.parquet"
- config_name: "rm-CH"
data_files:
- split: train
path: "data/rm-CH/*.parquet"
- config_name: "ro-AD"
data_files:
- split: train
path: "data/ro-AD/*.parquet"
- config_name: "ro-AI"
data_files:
- split: train
path: "data/ro-AI/*.parquet"
- config_name: "ro-AM"
data_files:
- split: train
path: "data/ro-AM/*.parquet"
- config_name: "ro-AR"
data_files:
- split: train
path: "data/ro-AR/*.parquet"
- config_name: "ro-AT"
data_files:
- split: train
path: "data/ro-AT/*.parquet"
- config_name: "ro-AU"
data_files:
- split: train
path: "data/ro-AU/*.parquet"
- config_name: "ro-BA"
data_files:
- split: train
path: "data/ro-BA/*.parquet"
- config_name: "ro-BE"
data_files:
- split: train
path: "data/ro-BE/*.parquet"
- config_name: "ro-BG"
data_files:
- split: train
path: "data/ro-BG/*.parquet"
- config_name: "ro-BR"
data_files:
- split: train
path: "data/ro-BR/*.parquet"
- config_name: "ro-BZ"
data_files:
- split: train
path: "data/ro-BZ/*.parquet"
- config_name: "ro-CA"
data_files:
- split: train
path: "data/ro-CA/*.parquet"
- config_name: "ro-CC"
data_files:
- split: train
path: "data/ro-CC/*.parquet"
- config_name: "ro-CF"
data_files:
- split: train
path: "data/ro-CF/*.parquet"
- config_name: "ro-CH"
data_files:
- split: train
path: "data/ro-CH/*.parquet"
- config_name: "ro-CL"
data_files:
- split: train
path: "data/ro-CL/*.parquet"
- config_name: "ro-CN"
data_files:
- split: train
path: "data/ro-CN/*.parquet"
- config_name: "ro-CO"
data_files:
- split: train
path: "data/ro-CO/*.parquet"
- config_name: "ro-CZ"
data_files:
- split: train
path: "data/ro-CZ/*.parquet"
- config_name: "ro-DE"
data_files:
- split: train
path: "data/ro-DE/*.parquet"
- config_name: "ro-DK"
data_files:
- split: train
path: "data/ro-DK/*.parquet"
- config_name: "ro-EE"
data_files:
- split: train
path: "data/ro-EE/*.parquet"
- config_name: "ro-ES"
data_files:
- split: train
path: "data/ro-ES/*.parquet"
- config_name: "ro-EU"
data_files:
- split: train
path: "data/ro-EU/*.parquet"
- config_name: "ro-FM"
data_files:
- split: train
path: "data/ro-FM/*.parquet"
- config_name: "ro-FR"
data_files:
- split: train
path: "data/ro-FR/*.parquet"
- config_name: "ro-GA"
data_files:
- split: train
path: "data/ro-GA/*.parquet"
- config_name: "ro-GB"
data_files:
- split: train
path: "data/ro-GB/*.parquet"
- config_name: "ro-GL"
data_files:
- split: train
path: "data/ro-GL/*.parquet"
- config_name: "ro-GQ"
data_files:
- split: train
path: "data/ro-GQ/*.parquet"
- config_name: "ro-GR"
data_files:
- split: train
path: "data/ro-GR/*.parquet"
- config_name: "ro-HR"
data_files:
- split: train
path: "data/ro-HR/*.parquet"
- config_name: "ro-HU"
data_files:
- split: train
path: "data/ro-HU/*.parquet"
- config_name: "ro-IE"
data_files:
- split: train
path: "data/ro-IE/*.parquet"
- config_name: "ro-IM"
data_files:
- split: train
path: "data/ro-IM/*.parquet"
- config_name: "ro-IN"
data_files:
- split: train
path: "data/ro-IN/*.parquet"
- config_name: "ro-IO"
data_files:
- split: train
path: "data/ro-IO/*.parquet"
- config_name: "ro-IR"
data_files:
- split: train
path: "data/ro-IR/*.parquet"
- config_name: "ro-IT"
data_files:
- split: train
path: "data/ro-IT/*.parquet"
- config_name: "ro-JP"
data_files:
- split: train
path: "data/ro-JP/*.parquet"
- config_name: "ro-KZ"
data_files:
- split: train
path: "data/ro-KZ/*.parquet"
- config_name: "ro-LA"
data_files:
- split: train
path: "data/ro-LA/*.parquet"
- config_name: "ro-LU"
data_files:
- split: train
path: "data/ro-LU/*.parquet"
- config_name: "ro-MD"
data_files:
- split: train
path: "data/ro-MD/*.parquet"
- config_name: "ro-ME"
data_files:
- split: train
path: "data/ro-ME/*.parquet"
- config_name: "ro-MK"
data_files:
- split: train
path: "data/ro-MK/*.parquet"
- config_name: "ro-ML"
data_files:
- split: train
path: "data/ro-ML/*.parquet"
- config_name: "ro-NL"
data_files:
- split: train
path: "data/ro-NL/*.parquet"
- config_name: "ro-NO"
data_files:
- split: train
path: "data/ro-NO/*.parquet"
- config_name: "ro-PL"
data_files:
- split: train
path: "data/ro-PL/*.parquet"
- config_name: "ro-PT"
data_files:
- split: train
path: "data/ro-PT/*.parquet"
- config_name: "ro-RO"
data_files:
- split: train
path: "data/ro-RO/*.parquet"
- config_name: "ro-RS"
data_files:
- split: train
path: "data/ro-RS/*.parquet"
- config_name: "ro-RU"
data_files:
- split: train
path: "data/ro-RU/*.parquet"
- config_name: "ro-SE"
data_files:
- split: train
path: "data/ro-SE/*.parquet"
- config_name: "ro-SK"
data_files:
- split: train
path: "data/ro-SK/*.parquet"
- config_name: "ro-SO"
data_files:
- split: train
path: "data/ro-SO/*.parquet"
- config_name: "ro-ST"
data_files:
- split: train
path: "data/ro-ST/*.parquet"
- config_name: "ro-TK"
data_files:
- split: train
path: "data/ro-TK/*.parquet"
- config_name: "ro-TL"
data_files:
- split: train
path: "data/ro-TL/*.parquet"
- config_name: "ro-TO"
data_files:
- split: train
path: "data/ro-TO/*.parquet"
- config_name: "ro-TV"
data_files:
- split: train
path: "data/ro-TV/*.parquet"
- config_name: "ro-UA"
data_files:
- split: train
path: "data/ro-UA/*.parquet"
- config_name: "ro-US"
data_files:
- split: train
path: "data/ro-US/*.parquet"
- config_name: "ro-VA"
data_files:
- split: train
path: "data/ro-VA/*.parquet"
- config_name: "ro-VN"
data_files:
- split: train
path: "data/ro-VN/*.parquet"
- config_name: "ro-WS"
data_files:
- split: train
path: "data/ro-WS/*.parquet"
- config_name: "ro-XX"
data_files:
- split: train
path: "data/ro-XX/*.parquet"
- config_name: "ru-AE"
data_files:
- split: train
path: "data/ru-AE/*.parquet"
- config_name: "ru-AG"
data_files:
- split: train
path: "data/ru-AG/*.parquet"
- config_name: "ru-AI"
data_files:
- split: train
path: "data/ru-AI/*.parquet"
- config_name: "ru-AL"
data_files:
- split: train
path: "data/ru-AL/*.parquet"
- config_name: "ru-AM"
data_files:
- split: train
path: "data/ru-AM/*.parquet"
- config_name: "ru-AR"
data_files:
- split: train
path: "data/ru-AR/*.parquet"
- config_name: "ru-AT"
data_files:
- split: train
path: "data/ru-AT/*.parquet"
- config_name: "ru-AU"
data_files:
- split: train
path: "data/ru-AU/*.parquet"
- config_name: "ru-AZ"
data_files:
- split: train
path: "data/ru-AZ/*.parquet"
- config_name: "ru-BA"
data_files:
- split: train
path: "data/ru-BA/*.parquet"
- config_name: "ru-BE"
data_files:
- split: train
path: "data/ru-BE/*.parquet"
- config_name: "ru-BG"
data_files:
- split: train
path: "data/ru-BG/*.parquet"
- config_name: "ru-BI"
data_files:
- split: train
path: "data/ru-BI/*.parquet"
- config_name: "ru-BM"
data_files:
- split: train
path: "data/ru-BM/*.parquet"
- config_name: "ru-BO"
data_files:
- split: train
path: "data/ru-BO/*.parquet"
- config_name: "ru-BR"
data_files:
- split: train
path: "data/ru-BR/*.parquet"
- config_name: "ru-BY"
data_files:
- split: train
path: "data/ru-BY/*.parquet"
- config_name: "ru-BZ"
data_files:
- split: train
path: "data/ru-BZ/*.parquet"
- config_name: "ru-CA"
data_files:
- split: train
path: "data/ru-CA/*.parquet"
- config_name: "ru-CC"
data_files:
- split: train
path: "data/ru-CC/*.parquet"
- config_name: "ru-CD"
data_files:
- split: train
path: "data/ru-CD/*.parquet"
- config_name: "ru-CF"
data_files:
- split: train
path: "data/ru-CF/*.parquet"
- config_name: "ru-CH"
data_files:
- split: train
path: "data/ru-CH/*.parquet"
- config_name: "ru-CL"
data_files:
- split: train
path: "data/ru-CL/*.parquet"
- config_name: "ru-CN"
data_files:
- split: train
path: "data/ru-CN/*.parquet"
- config_name: "ru-CO"
data_files:
- split: train
path: "data/ru-CO/*.parquet"
- config_name: "ru-CU"
data_files:
- split: train
path: "data/ru-CU/*.parquet"
- config_name: "ru-CX"
data_files:
- split: train
path: "data/ru-CX/*.parquet"
- config_name: "ru-CY"
data_files:
- split: train
path: "data/ru-CY/*.parquet"
- config_name: "ru-CZ"
data_files:
- split: train
path: "data/ru-CZ/*.parquet"
- config_name: "ru-DE"
data_files:
- split: train
path: "data/ru-DE/*.parquet"
- config_name: "ru-DJ"
data_files:
- split: train
path: "data/ru-DJ/*.parquet"
- config_name: "ru-DK"
data_files:
- split: train
path: "data/ru-DK/*.parquet"
- config_name: "ru-DM"
data_files:
- split: train
path: "data/ru-DM/*.parquet"
- config_name: "ru-DO"
data_files:
- split: train
path: "data/ru-DO/*.parquet"
- config_name: "ru-DZ"
data_files:
- split: train
path: "data/ru-DZ/*.parquet"
- config_name: "ru-EC"
data_files:
- split: train
path: "data/ru-EC/*.parquet"
- config_name: "ru-EE"
data_files:
- split: train
path: "data/ru-EE/*.parquet"
- config_name: "ru-EN"
data_files:
- split: train
path: "data/ru-EN/*.parquet"
- config_name: "ru-ES"
data_files:
- split: train
path: "data/ru-ES/*.parquet"
- config_name: "ru-EU"
data_files:
- split: train
path: "data/ru-EU/*.parquet"
- config_name: "ru-EX"
data_files:
- split: train
path: "data/ru-EX/*.parquet"
- config_name: "ru-FI"
data_files:
- split: train
path: "data/ru-FI/*.parquet"
- config_name: "ru-FM"
data_files:
- split: train
path: "data/ru-FM/*.parquet"
- config_name: "ru-FR"
data_files:
- split: train
path: "data/ru-FR/*.parquet"
- config_name: "ru-GA"
data_files:
- split: train
path: "data/ru-GA/*.parquet"
- config_name: "ru-GB"
data_files:
- split: train
path: "data/ru-GB/*.parquet"
- config_name: "ru-GE"
data_files:
- split: train
path: "data/ru-GE/*.parquet"
- config_name: "ru-GG"
data_files:
- split: train
path: "data/ru-GG/*.parquet"
- config_name: "ru-GQ"
data_files:
- split: train
path: "data/ru-GQ/*.parquet"
- config_name: "ru-GR"
data_files:
- split: train
path: "data/ru-GR/*.parquet"
- config_name: "ru-HK"
data_files:
- split: train
path: "data/ru-HK/*.parquet"
- config_name: "ru-HR"
data_files:
- split: train
path: "data/ru-HR/*.parquet"
- config_name: "ru-HT"
data_files:
- split: train
path: "data/ru-HT/*.parquet"
- config_name: "ru-HU"
data_files:
- split: train
path: "data/ru-HU/*.parquet"
- config_name: "ru-ID"
data_files:
- split: train
path: "data/ru-ID/*.parquet"
- config_name: "ru-IE"
data_files:
- split: train
path: "data/ru-IE/*.parquet"
- config_name: "ru-IL"
data_files:
- split: train
path: "data/ru-IL/*.parquet"
- config_name: "ru-IM"
data_files:
- split: train
path: "data/ru-IM/*.parquet"
- config_name: "ru-IN"
data_files:
- split: train
path: "data/ru-IN/*.parquet"
- config_name: "ru-IO"
data_files:
- split: train
path: "data/ru-IO/*.parquet"
- config_name: "ru-IR"
data_files:
- split: train
path: "data/ru-IR/*.parquet"
- config_name: "ru-IS"
data_files:
- split: train
path: "data/ru-IS/*.parquet"
- config_name: "ru-IT"
data_files:
- split: train
path: "data/ru-IT/*.parquet"
- config_name: "ru-JP"
data_files:
- split: train
path: "data/ru-JP/*.parquet"
- config_name: "ru-KA"
data_files:
- split: train
path: "data/ru-KA/*.parquet"
- config_name: "ru-KE"
data_files:
- split: train
path: "data/ru-KE/*.parquet"
- config_name: "ru-KG"
data_files:
- split: train
path: "data/ru-KG/*.parquet"
- config_name: "ru-KK"
data_files:
- split: train
path: "data/ru-KK/*.parquet"
- config_name: "ru-KP"
data_files:
- split: train
path: "data/ru-KP/*.parquet"
- config_name: "ru-KR"
data_files:
- split: train
path: "data/ru-KR/*.parquet"
- config_name: "ru-KY"
data_files:
- split: train
path: "data/ru-KY/*.parquet"
- config_name: "ru-KZ"
data_files:
- split: train
path: "data/ru-KZ/*.parquet"
- config_name: "ru-LA"
data_files:
- split: train
path: "data/ru-LA/*.parquet"
- config_name: "ru-LI"
data_files:
- split: train
path: "data/ru-LI/*.parquet"
- config_name: "ru-LK"
data_files:
- split: train
path: "data/ru-LK/*.parquet"
- config_name: "ru-LT"
data_files:
- split: train
path: "data/ru-LT/*.parquet"
- config_name: "ru-LU"
data_files:
- split: train
path: "data/ru-LU/*.parquet"
- config_name: "ru-LV"
data_files:
- split: train
path: "data/ru-LV/*.parquet"
- config_name: "ru-LY"
data_files:
- split: train
path: "data/ru-LY/*.parquet"
- config_name: "ru-MA"
data_files:
- split: train
path: "data/ru-MA/*.parquet"
- config_name: "ru-MD"
data_files:
- split: train
path: "data/ru-MD/*.parquet"
- config_name: "ru-ME"
data_files:
- split: train
path: "data/ru-ME/*.parquet"
- config_name: "ru-MG"
data_files:
- split: train
path: "data/ru-MG/*.parquet"
- config_name: "ru-MK"
data_files:
- split: train
path: "data/ru-MK/*.parquet"
- config_name: "ru-ML"
data_files:
- split: train
path: "data/ru-ML/*.parquet"
- config_name: "ru-MN"
data_files:
- split: train
path: "data/ru-MN/*.parquet"
- config_name: "ru-MS"
data_files:
- split: train
path: "data/ru-MS/*.parquet"
- config_name: "ru-MT"
data_files:
- split: train
path: "data/ru-MT/*.parquet"
- config_name: "ru-MU"
data_files:
- split: train
path: "data/ru-MU/*.parquet"
- config_name: "ru-MW"
data_files:
- split: train
path: "data/ru-MW/*.parquet"
- config_name: "ru-MX"
data_files:
- split: train
path: "data/ru-MX/*.parquet"
- config_name: "ru-MY"
data_files:
- split: train
path: "data/ru-MY/*.parquet"
- config_name: "ru-NG"
data_files:
- split: train
path: "data/ru-NG/*.parquet"
- config_name: "ru-NL"
data_files:
- split: train
path: "data/ru-NL/*.parquet"
- config_name: "ru-NO"
data_files:
- split: train
path: "data/ru-NO/*.parquet"
- config_name: "ru-NP"
data_files:
- split: train
path: "data/ru-NP/*.parquet"
- config_name: "ru-NU"
data_files:
- split: train
path: "data/ru-NU/*.parquet"
- config_name: "ru-NZ"
data_files:
- split: train
path: "data/ru-NZ/*.parquet"
- config_name: "ru-PE"
data_files:
- split: train
path: "data/ru-PE/*.parquet"
- config_name: "ru-PH"
data_files:
- split: train
path: "data/ru-PH/*.parquet"
- config_name: "ru-PK"
data_files:
- split: train
path: "data/ru-PK/*.parquet"
- config_name: "ru-PL"
data_files:
- split: train
path: "data/ru-PL/*.parquet"
- config_name: "ru-PM"
data_files:
- split: train
path: "data/ru-PM/*.parquet"
- config_name: "ru-PN"
data_files:
- split: train
path: "data/ru-PN/*.parquet"
- config_name: "ru-PT"
data_files:
- split: train
path: "data/ru-PT/*.parquet"
- config_name: "ru-PW"
data_files:
- split: train
path: "data/ru-PW/*.parquet"
- config_name: "ru-QA"
data_files:
- split: train
path: "data/ru-QA/*.parquet"
- config_name: "ru-QT"
data_files:
- split: train
path: "data/ru-QT/*.parquet"
- config_name: "ru-RE"
data_files:
- split: train
path: "data/ru-RE/*.parquet"
- config_name: "ru-RI"
data_files:
- split: train
path: "data/ru-RI/*.parquet"
- config_name: "ru-RO"
data_files:
- split: train
path: "data/ru-RO/*.parquet"
- config_name: "ru-RS"
data_files:
- split: train
path: "data/ru-RS/*.parquet"
- config_name: "ru-RU"
data_files:
- split: train
path: "data/ru-RU/*.parquet"
- config_name: "ru-SA"
data_files:
- split: train
path: "data/ru-SA/*.parquet"
- config_name: "ru-SC"
data_files:
- split: train
path: "data/ru-SC/*.parquet"
- config_name: "ru-SE"
data_files:
- split: train
path: "data/ru-SE/*.parquet"
- config_name: "ru-SG"
data_files:
- split: train
path: "data/ru-SG/*.parquet"
- config_name: "ru-SH"
data_files:
- split: train
path: "data/ru-SH/*.parquet"
- config_name: "ru-SI"
data_files:
- split: train
path: "data/ru-SI/*.parquet"
- config_name: "ru-SK"
data_files:
- split: train
path: "data/ru-SK/*.parquet"
- config_name: "ru-SO"
data_files:
- split: train
path: "data/ru-SO/*.parquet"
- config_name: "ru-SR"
data_files:
- split: train
path: "data/ru-SR/*.parquet"
- config_name: "ru-ST"
data_files:
- split: train
path: "data/ru-ST/*.parquet"
- config_name: "ru-SX"
data_files:
- split: train
path: "data/ru-SX/*.parquet"
- config_name: "ru-TC"
data_files:
- split: train
path: "data/ru-TC/*.parquet"
- config_name: "ru-TG"
data_files:
- split: train
path: "data/ru-TG/*.parquet"
- config_name: "ru-TH"
data_files:
- split: train
path: "data/ru-TH/*.parquet"
- config_name: "ru-TJ"
data_files:
- split: train
path: "data/ru-TJ/*.parquet"
- config_name: "ru-TK"
data_files:
- split: train
path: "data/ru-TK/*.parquet"
- config_name: "ru-TL"
data_files:
- split: train
path: "data/ru-TL/*.parquet"
- config_name: "ru-TM"
data_files:
- split: train
path: "data/ru-TM/*.parquet"
- config_name: "ru-TO"
data_files:
- split: train
path: "data/ru-TO/*.parquet"
- config_name: "ru-TR"
data_files:
- split: train
path: "data/ru-TR/*.parquet"
- config_name: "ru-TT"
data_files:
- split: train
path: "data/ru-TT/*.parquet"
- config_name: "ru-TV"
data_files:
- split: train
path: "data/ru-TV/*.parquet"
- config_name: "ru-TW"
data_files:
- split: train
path: "data/ru-TW/*.parquet"
- config_name: "ru-UA"
data_files:
- split: train
path: "data/ru-UA/*.parquet"
- config_name: "ru-UK"
data_files:
- split: train
path: "data/ru-UK/*.parquet"
- config_name: "ru-US"
data_files:
- split: train
path: "data/ru-US/*.parquet"
- config_name: "ru-UY"
data_files:
- split: train
path: "data/ru-UY/*.parquet"
- config_name: "ru-UZ"
data_files:
- split: train
path: "data/ru-UZ/*.parquet"
- config_name: "ru-VA"
data_files:
- split: train
path: "data/ru-VA/*.parquet"
- config_name: "ru-VC"
data_files:
- split: train
path: "data/ru-VC/*.parquet"
- config_name: "ru-VE"
data_files:
- split: train
path: "data/ru-VE/*.parquet"
- config_name: "ru-VG"
data_files:
- split: train
path: "data/ru-VG/*.parquet"
- config_name: "ru-VN"
data_files:
- split: train
path: "data/ru-VN/*.parquet"
- config_name: "ru-WF"
data_files:
- split: train
path: "data/ru-WF/*.parquet"
- config_name: "ru-WO"
data_files:
- split: train
path: "data/ru-WO/*.parquet"
- config_name: "ru-WS"
data_files:
- split: train
path: "data/ru-WS/*.parquet"
- config_name: "ru-XX"
data_files:
- split: train
path: "data/ru-XX/*.parquet"
- config_name: "ru-YU"
data_files:
- split: train
path: "data/ru-YU/*.parquet"
- config_name: "ru-ZA"
data_files:
- split: train
path: "data/ru-ZA/*.parquet"
- config_name: "sah-RU"
data_files:
- split: train
path: "data/sah-RU/*.parquet"
- config_name: "sah-XX"
data_files:
- split: train
path: "data/sah-XX/*.parquet"
- config_name: "scn-XX"
data_files:
- split: train
path: "data/scn-XX/*.parquet"
- config_name: "sd-ES"
data_files:
- split: train
path: "data/sd-ES/*.parquet"
- config_name: "sd-GB"
data_files:
- split: train
path: "data/sd-GB/*.parquet"
- config_name: "sd-PK"
data_files:
- split: train
path: "data/sd-PK/*.parquet"
- config_name: "sd-TV"
data_files:
- split: train
path: "data/sd-TV/*.parquet"
- config_name: "sd-US"
data_files:
- split: train
path: "data/sd-US/*.parquet"
- config_name: "sd-XX"
data_files:
- split: train
path: "data/sd-XX/*.parquet"
- config_name: "sh-BA"
data_files:
- split: train
path: "data/sh-BA/*.parquet"
- config_name: "sh-RS"
data_files:
- split: train
path: "data/sh-RS/*.parquet"
- config_name: "sh-US"
data_files:
- split: train
path: "data/sh-US/*.parquet"
- config_name: "sh-XX"
data_files:
- split: train
path: "data/sh-XX/*.parquet"
- config_name: "sh-YU"
data_files:
- split: train
path: "data/sh-YU/*.parquet"
- config_name: "si-GB"
data_files:
- split: train
path: "data/si-GB/*.parquet"
- config_name: "si-LK"
data_files:
- split: train
path: "data/si-LK/*.parquet"
- config_name: "si-US"
data_files:
- split: train
path: "data/si-US/*.parquet"
- config_name: "si-XX"
data_files:
- split: train
path: "data/si-XX/*.parquet"
- config_name: "sk-AG"
data_files:
- split: train
path: "data/sk-AG/*.parquet"
- config_name: "sk-AT"
data_files:
- split: train
path: "data/sk-AT/*.parquet"
- config_name: "sk-BM"
data_files:
- split: train
path: "data/sk-BM/*.parquet"
- config_name: "sk-CA"
data_files:
- split: train
path: "data/sk-CA/*.parquet"
- config_name: "sk-CC"
data_files:
- split: train
path: "data/sk-CC/*.parquet"
- config_name: "sk-CH"
data_files:
- split: train
path: "data/sk-CH/*.parquet"
- config_name: "sk-CN"
data_files:
- split: train
path: "data/sk-CN/*.parquet"
- config_name: "sk-CO"
data_files:
- split: train
path: "data/sk-CO/*.parquet"
- config_name: "sk-CZ"
data_files:
- split: train
path: "data/sk-CZ/*.parquet"
- config_name: "sk-DE"
data_files:
- split: train
path: "data/sk-DE/*.parquet"
- config_name: "sk-DK"
data_files:
- split: train
path: "data/sk-DK/*.parquet"
- config_name: "sk-EE"
data_files:
- split: train
path: "data/sk-EE/*.parquet"
- config_name: "sk-ES"
data_files:
- split: train
path: "data/sk-ES/*.parquet"
- config_name: "sk-EU"
data_files:
- split: train
path: "data/sk-EU/*.parquet"
- config_name: "sk-FI"
data_files:
- split: train
path: "data/sk-FI/*.parquet"
- config_name: "sk-FM"
data_files:
- split: train
path: "data/sk-FM/*.parquet"
- config_name: "sk-FR"
data_files:
- split: train
path: "data/sk-FR/*.parquet"
- config_name: "sk-GB"
data_files:
- split: train
path: "data/sk-GB/*.parquet"
- config_name: "sk-GR"
data_files:
- split: train
path: "data/sk-GR/*.parquet"
- config_name: "sk-HK"
data_files:
- split: train
path: "data/sk-HK/*.parquet"
- config_name: "sk-HR"
data_files:
- split: train
path: "data/sk-HR/*.parquet"
- config_name: "sk-HU"
data_files:
- split: train
path: "data/sk-HU/*.parquet"
- config_name: "sk-IO"
data_files:
- split: train
path: "data/sk-IO/*.parquet"
- config_name: "sk-IS"
data_files:
- split: train
path: "data/sk-IS/*.parquet"
- config_name: "sk-IT"
data_files:
- split: train
path: "data/sk-IT/*.parquet"
- config_name: "sk-LT"
data_files:
- split: train
path: "data/sk-LT/*.parquet"
- config_name: "sk-LV"
data_files:
- split: train
path: "data/sk-LV/*.parquet"
- config_name: "sk-ME"
data_files:
- split: train
path: "data/sk-ME/*.parquet"
- config_name: "sk-MK"
data_files:
- split: train
path: "data/sk-MK/*.parquet"
- config_name: "sk-NL"
data_files:
- split: train
path: "data/sk-NL/*.parquet"
- config_name: "sk-PL"
data_files:
- split: train
path: "data/sk-PL/*.parquet"
- config_name: "sk-PT"
data_files:
- split: train
path: "data/sk-PT/*.parquet"
- config_name: "sk-RO"
data_files:
- split: train
path: "data/sk-RO/*.parquet"
- config_name: "sk-RS"
data_files:
- split: train
path: "data/sk-RS/*.parquet"
- config_name: "sk-RU"
data_files:
- split: train
path: "data/sk-RU/*.parquet"
- config_name: "sk-SE"
data_files:
- split: train
path: "data/sk-SE/*.parquet"
- config_name: "sk-SG"
data_files:
- split: train
path: "data/sk-SG/*.parquet"
- config_name: "sk-SI"
data_files:
- split: train
path: "data/sk-SI/*.parquet"
- config_name: "sk-SK"
data_files:
- split: train
path: "data/sk-SK/*.parquet"
- config_name: "sk-TO"
data_files:
- split: train
path: "data/sk-TO/*.parquet"
- config_name: "sk-TV"
data_files:
- split: train
path: "data/sk-TV/*.parquet"
- config_name: "sk-UA"
data_files:
- split: train
path: "data/sk-UA/*.parquet"
- config_name: "sk-US"
data_files:
- split: train
path: "data/sk-US/*.parquet"
- config_name: "sk-VA"
data_files:
- split: train
path: "data/sk-VA/*.parquet"
- config_name: "sk-WS"
data_files:
- split: train
path: "data/sk-WS/*.parquet"
- config_name: "sk-XX"
data_files:
- split: train
path: "data/sk-XX/*.parquet"
- config_name: "sl-AT"
data_files:
- split: train
path: "data/sl-AT/*.parquet"
- config_name: "sl-BG"
data_files:
- split: train
path: "data/sl-BG/*.parquet"
- config_name: "sl-BR"
data_files:
- split: train
path: "data/sl-BR/*.parquet"
- config_name: "sl-CA"
data_files:
- split: train
path: "data/sl-CA/*.parquet"
- config_name: "sl-CC"
data_files:
- split: train
path: "data/sl-CC/*.parquet"
- config_name: "sl-CH"
data_files:
- split: train
path: "data/sl-CH/*.parquet"
- config_name: "sl-CN"
data_files:
- split: train
path: "data/sl-CN/*.parquet"
- config_name: "sl-CO"
data_files:
- split: train
path: "data/sl-CO/*.parquet"
- config_name: "sl-CZ"
data_files:
- split: train
path: "data/sl-CZ/*.parquet"
- config_name: "sl-DE"
data_files:
- split: train
path: "data/sl-DE/*.parquet"
- config_name: "sl-DK"
data_files:
- split: train
path: "data/sl-DK/*.parquet"
- config_name: "sl-EE"
data_files:
- split: train
path: "data/sl-EE/*.parquet"
- config_name: "sl-ES"
data_files:
- split: train
path: "data/sl-ES/*.parquet"
- config_name: "sl-EU"
data_files:
- split: train
path: "data/sl-EU/*.parquet"
- config_name: "sl-FI"
data_files:
- split: train
path: "data/sl-FI/*.parquet"
- config_name: "sl-FR"
data_files:
- split: train
path: "data/sl-FR/*.parquet"
- config_name: "sl-GB"
data_files:
- split: train
path: "data/sl-GB/*.parquet"
- config_name: "sl-HR"
data_files:
- split: train
path: "data/sl-HR/*.parquet"
- config_name: "sl-HU"
data_files:
- split: train
path: "data/sl-HU/*.parquet"
- config_name: "sl-IO"
data_files:
- split: train
path: "data/sl-IO/*.parquet"
- config_name: "sl-IT"
data_files:
- split: train
path: "data/sl-IT/*.parquet"
- config_name: "sl-JE"
data_files:
- split: train
path: "data/sl-JE/*.parquet"
- config_name: "sl-JP"
data_files:
- split: train
path: "data/sl-JP/*.parquet"
- config_name: "sl-KS"
data_files:
- split: train
path: "data/sl-KS/*.parquet"
- config_name: "sl-ME"
data_files:
- split: train
path: "data/sl-ME/*.parquet"
- config_name: "sl-MS"
data_files:
- split: train
path: "data/sl-MS/*.parquet"
- config_name: "sl-NL"
data_files:
- split: train
path: "data/sl-NL/*.parquet"
- config_name: "sl-NZ"
data_files:
- split: train
path: "data/sl-NZ/*.parquet"
- config_name: "sl-PL"
data_files:
- split: train
path: "data/sl-PL/*.parquet"
- config_name: "sl-PT"
data_files:
- split: train
path: "data/sl-PT/*.parquet"
- config_name: "sl-RE"
data_files:
- split: train
path: "data/sl-RE/*.parquet"
- config_name: "sl-RO"
data_files:
- split: train
path: "data/sl-RO/*.parquet"
- config_name: "sl-RS"
data_files:
- split: train
path: "data/sl-RS/*.parquet"
- config_name: "sl-RU"
data_files:
- split: train
path: "data/sl-RU/*.parquet"
- config_name: "sl-SE"
data_files:
- split: train
path: "data/sl-SE/*.parquet"
- config_name: "sl-SI"
data_files:
- split: train
path: "data/sl-SI/*.parquet"
- config_name: "sl-SK"
data_files:
- split: train
path: "data/sl-SK/*.parquet"
- config_name: "sl-SL"
data_files:
- split: train
path: "data/sl-SL/*.parquet"
- config_name: "sl-TL"
data_files:
- split: train
path: "data/sl-TL/*.parquet"
- config_name: "sl-TV"
data_files:
- split: train
path: "data/sl-TV/*.parquet"
- config_name: "sl-US"
data_files:
- split: train
path: "data/sl-US/*.parquet"
- config_name: "sl-VA"
data_files:
- split: train
path: "data/sl-VA/*.parquet"
- config_name: "sl-WS"
data_files:
- split: train
path: "data/sl-WS/*.parquet"
- config_name: "sl-XX"
data_files:
- split: train
path: "data/sl-XX/*.parquet"
- config_name: "sq-AL"
data_files:
- split: train
path: "data/sq-AL/*.parquet"
- config_name: "sq-AU"
data_files:
- split: train
path: "data/sq-AU/*.parquet"
- config_name: "sq-BE"
data_files:
- split: train
path: "data/sq-BE/*.parquet"
- config_name: "sq-BG"
data_files:
- split: train
path: "data/sq-BG/*.parquet"
- config_name: "sq-BR"
data_files:
- split: train
path: "data/sq-BR/*.parquet"
- config_name: "sq-CA"
data_files:
- split: train
path: "data/sq-CA/*.parquet"
- config_name: "sq-CC"
data_files:
- split: train
path: "data/sq-CC/*.parquet"
- config_name: "sq-CH"
data_files:
- split: train
path: "data/sq-CH/*.parquet"
- config_name: "sq-CN"
data_files:
- split: train
path: "data/sq-CN/*.parquet"
- config_name: "sq-CO"
data_files:
- split: train
path: "data/sq-CO/*.parquet"
- config_name: "sq-CZ"
data_files:
- split: train
path: "data/sq-CZ/*.parquet"
- config_name: "sq-DE"
data_files:
- split: train
path: "data/sq-DE/*.parquet"
- config_name: "sq-DK"
data_files:
- split: train
path: "data/sq-DK/*.parquet"
- config_name: "sq-EN"
data_files:
- split: train
path: "data/sq-EN/*.parquet"
- config_name: "sq-EU"
data_files:
- split: train
path: "data/sq-EU/*.parquet"
- config_name: "sq-FM"
data_files:
- split: train
path: "data/sq-FM/*.parquet"
- config_name: "sq-FR"
data_files:
- split: train
path: "data/sq-FR/*.parquet"
- config_name: "sq-GB"
data_files:
- split: train
path: "data/sq-GB/*.parquet"
- config_name: "sq-GR"
data_files:
- split: train
path: "data/sq-GR/*.parquet"
- config_name: "sq-IN"
data_files:
- split: train
path: "data/sq-IN/*.parquet"
- config_name: "sq-IR"
data_files:
- split: train
path: "data/sq-IR/*.parquet"
- config_name: "sq-IS"
data_files:
- split: train
path: "data/sq-IS/*.parquet"
- config_name: "sq-IT"
data_files:
- split: train
path: "data/sq-IT/*.parquet"
- config_name: "sq-KS"
data_files:
- split: train
path: "data/sq-KS/*.parquet"
- config_name: "sq-LT"
data_files:
- split: train
path: "data/sq-LT/*.parquet"
- config_name: "sq-ME"
data_files:
- split: train
path: "data/sq-ME/*.parquet"
- config_name: "sq-MK"
data_files:
- split: train
path: "data/sq-MK/*.parquet"
- config_name: "sq-NO"
data_files:
- split: train
path: "data/sq-NO/*.parquet"
- config_name: "sq-RS"
data_files:
- split: train
path: "data/sq-RS/*.parquet"
- config_name: "sq-RU"
data_files:
- split: train
path: "data/sq-RU/*.parquet"
- config_name: "sq-SH"
data_files:
- split: train
path: "data/sq-SH/*.parquet"
- config_name: "sq-SQ"
data_files:
- split: train
path: "data/sq-SQ/*.parquet"
- config_name: "sq-TL"
data_files:
- split: train
path: "data/sq-TL/*.parquet"
- config_name: "sq-TV"
data_files:
- split: train
path: "data/sq-TV/*.parquet"
- config_name: "sq-UA"
data_files:
- split: train
path: "data/sq-UA/*.parquet"
- config_name: "sq-US"
data_files:
- split: train
path: "data/sq-US/*.parquet"
- config_name: "sq-VA"
data_files:
- split: train
path: "data/sq-VA/*.parquet"
- config_name: "sq-XK"
data_files:
- split: train
path: "data/sq-XK/*.parquet"
- config_name: "sq-XX"
data_files:
- split: train
path: "data/sq-XX/*.parquet"
- config_name: "sr-AT"
data_files:
- split: train
path: "data/sr-AT/*.parquet"
- config_name: "sr-BA"
data_files:
- split: train
path: "data/sr-BA/*.parquet"
- config_name: "sr-BE"
data_files:
- split: train
path: "data/sr-BE/*.parquet"
- config_name: "sr-BG"
data_files:
- split: train
path: "data/sr-BG/*.parquet"
- config_name: "sr-BZ"
data_files:
- split: train
path: "data/sr-BZ/*.parquet"
- config_name: "sr-CA"
data_files:
- split: train
path: "data/sr-CA/*.parquet"
- config_name: "sr-CC"
data_files:
- split: train
path: "data/sr-CC/*.parquet"
- config_name: "sr-CH"
data_files:
- split: train
path: "data/sr-CH/*.parquet"
- config_name: "sr-CI"
data_files:
- split: train
path: "data/sr-CI/*.parquet"
- config_name: "sr-CN"
data_files:
- split: train
path: "data/sr-CN/*.parquet"
- config_name: "sr-CO"
data_files:
- split: train
path: "data/sr-CO/*.parquet"
- config_name: "sr-CR"
data_files:
- split: train
path: "data/sr-CR/*.parquet"
- config_name: "sr-CS"
data_files:
- split: train
path: "data/sr-CS/*.parquet"
- config_name: "sr-DE"
data_files:
- split: train
path: "data/sr-DE/*.parquet"
- config_name: "sr-ES"
data_files:
- split: train
path: "data/sr-ES/*.parquet"
- config_name: "sr-EU"
data_files:
- split: train
path: "data/sr-EU/*.parquet"
- config_name: "sr-FR"
data_files:
- split: train
path: "data/sr-FR/*.parquet"
- config_name: "sr-GB"
data_files:
- split: train
path: "data/sr-GB/*.parquet"
- config_name: "sr-HR"
data_files:
- split: train
path: "data/sr-HR/*.parquet"
- config_name: "sr-HU"
data_files:
- split: train
path: "data/sr-HU/*.parquet"
- config_name: "sr-IN"
data_files:
- split: train
path: "data/sr-IN/*.parquet"
- config_name: "sr-IS"
data_files:
- split: train
path: "data/sr-IS/*.parquet"
- config_name: "sr-IT"
data_files:
- split: train
path: "data/sr-IT/*.parquet"
- config_name: "sr-JP"
data_files:
- split: train
path: "data/sr-JP/*.parquet"
- config_name: "sr-LA"
data_files:
- split: train
path: "data/sr-LA/*.parquet"
- config_name: "sr-LT"
data_files:
- split: train
path: "data/sr-LT/*.parquet"
- config_name: "sr-ME"
data_files:
- split: train
path: "data/sr-ME/*.parquet"
- config_name: "sr-MK"
data_files:
- split: train
path: "data/sr-MK/*.parquet"
- config_name: "sr-NL"
data_files:
- split: train
path: "data/sr-NL/*.parquet"
- config_name: "sr-NZ"
data_files:
- split: train
path: "data/sr-NZ/*.parquet"
- config_name: "sr-PL"
data_files:
- split: train
path: "data/sr-PL/*.parquet"
- config_name: "sr-PW"
data_files:
- split: train
path: "data/sr-PW/*.parquet"
- config_name: "sr-RO"
data_files:
- split: train
path: "data/sr-RO/*.parquet"
- config_name: "sr-RS"
data_files:
- split: train
path: "data/sr-RS/*.parquet"
- config_name: "sr-RU"
data_files:
- split: train
path: "data/sr-RU/*.parquet"
- config_name: "sr-SE"
data_files:
- split: train
path: "data/sr-SE/*.parquet"
- config_name: "sr-SK"
data_files:
- split: train
path: "data/sr-SK/*.parquet"
- config_name: "sr-SR"
data_files:
- split: train
path: "data/sr-SR/*.parquet"
- config_name: "sr-TM"
data_files:
- split: train
path: "data/sr-TM/*.parquet"
- config_name: "sr-TV"
data_files:
- split: train
path: "data/sr-TV/*.parquet"
- config_name: "sr-UA"
data_files:
- split: train
path: "data/sr-UA/*.parquet"
- config_name: "sr-US"
data_files:
- split: train
path: "data/sr-US/*.parquet"
- config_name: "sr-WS"
data_files:
- split: train
path: "data/sr-WS/*.parquet"
- config_name: "sr-XX"
data_files:
- split: train
path: "data/sr-XX/*.parquet"
- config_name: "sr-YU"
data_files:
- split: train
path: "data/sr-YU/*.parquet"
- config_name: "su-ST"
data_files:
- split: train
path: "data/su-ST/*.parquet"
- config_name: "su-XX"
data_files:
- split: train
path: "data/su-XX/*.parquet"
- config_name: "sv-AD"
data_files:
- split: train
path: "data/sv-AD/*.parquet"
- config_name: "sv-AE"
data_files:
- split: train
path: "data/sv-AE/*.parquet"
- config_name: "sv-AI"
data_files:
- split: train
path: "data/sv-AI/*.parquet"
- config_name: "sv-AR"
data_files:
- split: train
path: "data/sv-AR/*.parquet"
- config_name: "sv-AS"
data_files:
- split: train
path: "data/sv-AS/*.parquet"
- config_name: "sv-AT"
data_files:
- split: train
path: "data/sv-AT/*.parquet"
- config_name: "sv-AU"
data_files:
- split: train
path: "data/sv-AU/*.parquet"
- config_name: "sv-AX"
data_files:
- split: train
path: "data/sv-AX/*.parquet"
- config_name: "sv-AZ"
data_files:
- split: train
path: "data/sv-AZ/*.parquet"
- config_name: "sv-BA"
data_files:
- split: train
path: "data/sv-BA/*.parquet"
- config_name: "sv-BE"
data_files:
- split: train
path: "data/sv-BE/*.parquet"
- config_name: "sv-BG"
data_files:
- split: train
path: "data/sv-BG/*.parquet"
- config_name: "sv-BM"
data_files:
- split: train
path: "data/sv-BM/*.parquet"
- config_name: "sv-BR"
data_files:
- split: train
path: "data/sv-BR/*.parquet"
- config_name: "sv-BZ"
data_files:
- split: train
path: "data/sv-BZ/*.parquet"
- config_name: "sv-CA"
data_files:
- split: train
path: "data/sv-CA/*.parquet"
- config_name: "sv-CC"
data_files:
- split: train
path: "data/sv-CC/*.parquet"
- config_name: "sv-CF"
data_files:
- split: train
path: "data/sv-CF/*.parquet"
- config_name: "sv-CH"
data_files:
- split: train
path: "data/sv-CH/*.parquet"
- config_name: "sv-CN"
data_files:
- split: train
path: "data/sv-CN/*.parquet"
- config_name: "sv-CO"
data_files:
- split: train
path: "data/sv-CO/*.parquet"
- config_name: "sv-CY"
data_files:
- split: train
path: "data/sv-CY/*.parquet"
- config_name: "sv-CZ"
data_files:
- split: train
path: "data/sv-CZ/*.parquet"
- config_name: "sv-DE"
data_files:
- split: train
path: "data/sv-DE/*.parquet"
- config_name: "sv-DK"
data_files:
- split: train
path: "data/sv-DK/*.parquet"
- config_name: "sv-DO"
data_files:
- split: train
path: "data/sv-DO/*.parquet"
- config_name: "sv-EE"
data_files:
- split: train
path: "data/sv-EE/*.parquet"
- config_name: "sv-EN"
data_files:
- split: train
path: "data/sv-EN/*.parquet"
- config_name: "sv-ES"
data_files:
- split: train
path: "data/sv-ES/*.parquet"
- config_name: "sv-EU"
data_files:
- split: train
path: "data/sv-EU/*.parquet"
- config_name: "sv-FI"
data_files:
- split: train
path: "data/sv-FI/*.parquet"
- config_name: "sv-FM"
data_files:
- split: train
path: "data/sv-FM/*.parquet"
- config_name: "sv-FO"
data_files:
- split: train
path: "data/sv-FO/*.parquet"
- config_name: "sv-FR"
data_files:
- split: train
path: "data/sv-FR/*.parquet"
- config_name: "sv-GA"
data_files:
- split: train
path: "data/sv-GA/*.parquet"
- config_name: "sv-GB"
data_files:
- split: train
path: "data/sv-GB/*.parquet"
- config_name: "sv-GG"
data_files:
- split: train
path: "data/sv-GG/*.parquet"
- config_name: "sv-GR"
data_files:
- split: train
path: "data/sv-GR/*.parquet"
- config_name: "sv-HR"
data_files:
- split: train
path: "data/sv-HR/*.parquet"
- config_name: "sv-HU"
data_files:
- split: train
path: "data/sv-HU/*.parquet"
- config_name: "sv-ID"
data_files:
- split: train
path: "data/sv-ID/*.parquet"
- config_name: "sv-IE"
data_files:
- split: train
path: "data/sv-IE/*.parquet"
- config_name: "sv-IL"
data_files:
- split: train
path: "data/sv-IL/*.parquet"
- config_name: "sv-IN"
data_files:
- split: train
path: "data/sv-IN/*.parquet"
- config_name: "sv-IO"
data_files:
- split: train
path: "data/sv-IO/*.parquet"
- config_name: "sv-IR"
data_files:
- split: train
path: "data/sv-IR/*.parquet"
- config_name: "sv-IS"
data_files:
- split: train
path: "data/sv-IS/*.parquet"
- config_name: "sv-IT"
data_files:
- split: train
path: "data/sv-IT/*.parquet"
- config_name: "sv-JP"
data_files:
- split: train
path: "data/sv-JP/*.parquet"
- config_name: "sv-KR"
data_files:
- split: train
path: "data/sv-KR/*.parquet"
- config_name: "sv-KW"
data_files:
- split: train
path: "data/sv-KW/*.parquet"
- config_name: "sv-KZ"
data_files:
- split: train
path: "data/sv-KZ/*.parquet"
- config_name: "sv-LA"
data_files:
- split: train
path: "data/sv-LA/*.parquet"
- config_name: "sv-LK"
data_files:
- split: train
path: "data/sv-LK/*.parquet"
- config_name: "sv-LT"
data_files:
- split: train
path: "data/sv-LT/*.parquet"
- config_name: "sv-LV"
data_files:
- split: train
path: "data/sv-LV/*.parquet"
- config_name: "sv-MD"
data_files:
- split: train
path: "data/sv-MD/*.parquet"
- config_name: "sv-ME"
data_files:
- split: train
path: "data/sv-ME/*.parquet"
- config_name: "sv-MT"
data_files:
- split: train
path: "data/sv-MT/*.parquet"
- config_name: "sv-MX"
data_files:
- split: train
path: "data/sv-MX/*.parquet"
- config_name: "sv-NG"
data_files:
- split: train
path: "data/sv-NG/*.parquet"
- config_name: "sv-NL"
data_files:
- split: train
path: "data/sv-NL/*.parquet"
- config_name: "sv-NO"
data_files:
- split: train
path: "data/sv-NO/*.parquet"
- config_name: "sv-NU"
data_files:
- split: train
path: "data/sv-NU/*.parquet"
- config_name: "sv-NZ"
data_files:
- split: train
path: "data/sv-NZ/*.parquet"
- config_name: "sv-PE"
data_files:
- split: train
path: "data/sv-PE/*.parquet"
- config_name: "sv-PL"
data_files:
- split: train
path: "data/sv-PL/*.parquet"
- config_name: "sv-PM"
data_files:
- split: train
path: "data/sv-PM/*.parquet"
- config_name: "sv-PT"
data_files:
- split: train
path: "data/sv-PT/*.parquet"
- config_name: "sv-PW"
data_files:
- split: train
path: "data/sv-PW/*.parquet"
- config_name: "sv-RE"
data_files:
- split: train
path: "data/sv-RE/*.parquet"
- config_name: "sv-RO"
data_files:
- split: train
path: "data/sv-RO/*.parquet"
- config_name: "sv-RS"
data_files:
- split: train
path: "data/sv-RS/*.parquet"
- config_name: "sv-RU"
data_files:
- split: train
path: "data/sv-RU/*.parquet"
- config_name: "sv-SA"
data_files:
- split: train
path: "data/sv-SA/*.parquet"
- config_name: "sv-SE"
data_files:
- split: train
path: "data/sv-SE/*.parquet"
- config_name: "sv-SI"
data_files:
- split: train
path: "data/sv-SI/*.parquet"
- config_name: "sv-SK"
data_files:
- split: train
path: "data/sv-SK/*.parquet"
- config_name: "sv-ST"
data_files:
- split: train
path: "data/sv-ST/*.parquet"
- config_name: "sv-SV"
data_files:
- split: train
path: "data/sv-SV/*.parquet"
- config_name: "sv-SW"
data_files:
- split: train
path: "data/sv-SW/*.parquet"
- config_name: "sv-TK"
data_files:
- split: train
path: "data/sv-TK/*.parquet"
- config_name: "sv-TO"
data_files:
- split: train
path: "data/sv-TO/*.parquet"
- config_name: "sv-TR"
data_files:
- split: train
path: "data/sv-TR/*.parquet"
- config_name: "sv-TV"
data_files:
- split: train
path: "data/sv-TV/*.parquet"
- config_name: "sv-TW"
data_files:
- split: train
path: "data/sv-TW/*.parquet"
- config_name: "sv-UA"
data_files:
- split: train
path: "data/sv-UA/*.parquet"
- config_name: "sv-US"
data_files:
- split: train
path: "data/sv-US/*.parquet"
- config_name: "sv-VA"
data_files:
- split: train
path: "data/sv-VA/*.parquet"
- config_name: "sv-VN"
data_files:
- split: train
path: "data/sv-VN/*.parquet"
- config_name: "sv-WS"
data_files:
- split: train
path: "data/sv-WS/*.parquet"
- config_name: "sv-XX"
data_files:
- split: train
path: "data/sv-XX/*.parquet"
- config_name: "sw-CN"
data_files:
- split: train
path: "data/sw-CN/*.parquet"
- config_name: "sw-FR"
data_files:
- split: train
path: "data/sw-FR/*.parquet"
- config_name: "sw-GB"
data_files:
- split: train
path: "data/sw-GB/*.parquet"
- config_name: "sw-KE"
data_files:
- split: train
path: "data/sw-KE/*.parquet"
- config_name: "sw-RU"
data_files:
- split: train
path: "data/sw-RU/*.parquet"
- config_name: "sw-TR"
data_files:
- split: train
path: "data/sw-TR/*.parquet"
- config_name: "sw-TZ"
data_files:
- split: train
path: "data/sw-TZ/*.parquet"
- config_name: "sw-US"
data_files:
- split: train
path: "data/sw-US/*.parquet"
- config_name: "sw-XX"
data_files:
- split: train
path: "data/sw-XX/*.parquet"
- config_name: "ta-CA"
data_files:
- split: train
path: "data/ta-CA/*.parquet"
- config_name: "ta-CF"
data_files:
- split: train
path: "data/ta-CF/*.parquet"
- config_name: "ta-DE"
data_files:
- split: train
path: "data/ta-DE/*.parquet"
- config_name: "ta-GB"
data_files:
- split: train
path: "data/ta-GB/*.parquet"
- config_name: "ta-IN"
data_files:
- split: train
path: "data/ta-IN/*.parquet"
- config_name: "ta-IT"
data_files:
- split: train
path: "data/ta-IT/*.parquet"
- config_name: "ta-LK"
data_files:
- split: train
path: "data/ta-LK/*.parquet"
- config_name: "ta-ME"
data_files:
- split: train
path: "data/ta-ME/*.parquet"
- config_name: "ta-RU"
data_files:
- split: train
path: "data/ta-RU/*.parquet"
- config_name: "ta-SG"
data_files:
- split: train
path: "data/ta-SG/*.parquet"
- config_name: "ta-US"
data_files:
- split: train
path: "data/ta-US/*.parquet"
- config_name: "ta-XX"
data_files:
- split: train
path: "data/ta-XX/*.parquet"
- config_name: "te-GB"
data_files:
- split: train
path: "data/te-GB/*.parquet"
- config_name: "te-IN"
data_files:
- split: train
path: "data/te-IN/*.parquet"
- config_name: "te-NL"
data_files:
- split: train
path: "data/te-NL/*.parquet"
- config_name: "te-RU"
data_files:
- split: train
path: "data/te-RU/*.parquet"
- config_name: "te-TE"
data_files:
- split: train
path: "data/te-TE/*.parquet"
- config_name: "te-US"
data_files:
- split: train
path: "data/te-US/*.parquet"
- config_name: "te-XX"
data_files:
- split: train
path: "data/te-XX/*.parquet"
- config_name: "tg-AM"
data_files:
- split: train
path: "data/tg-AM/*.parquet"
- config_name: "tg-BE"
data_files:
- split: train
path: "data/tg-BE/*.parquet"
- config_name: "tg-BR"
data_files:
- split: train
path: "data/tg-BR/*.parquet"
- config_name: "tg-CA"
data_files:
- split: train
path: "data/tg-CA/*.parquet"
- config_name: "tg-DE"
data_files:
- split: train
path: "data/tg-DE/*.parquet"
- config_name: "tg-EU"
data_files:
- split: train
path: "data/tg-EU/*.parquet"
- config_name: "tg-FR"
data_files:
- split: train
path: "data/tg-FR/*.parquet"
- config_name: "tg-GB"
data_files:
- split: train
path: "data/tg-GB/*.parquet"
- config_name: "tg-IN"
data_files:
- split: train
path: "data/tg-IN/*.parquet"
- config_name: "tg-IR"
data_files:
- split: train
path: "data/tg-IR/*.parquet"
- config_name: "tg-IS"
data_files:
- split: train
path: "data/tg-IS/*.parquet"
- config_name: "tg-KZ"
data_files:
- split: train
path: "data/tg-KZ/*.parquet"
- config_name: "tg-RU"
data_files:
- split: train
path: "data/tg-RU/*.parquet"
- config_name: "tg-TG"
data_files:
- split: train
path: "data/tg-TG/*.parquet"
- config_name: "tg-TJ"
data_files:
- split: train
path: "data/tg-TJ/*.parquet"
- config_name: "tg-TV"
data_files:
- split: train
path: "data/tg-TV/*.parquet"
- config_name: "tg-UA"
data_files:
- split: train
path: "data/tg-UA/*.parquet"
- config_name: "tg-US"
data_files:
- split: train
path: "data/tg-US/*.parquet"
- config_name: "tg-UZ"
data_files:
- split: train
path: "data/tg-UZ/*.parquet"
- config_name: "tg-XX"
data_files:
- split: train
path: "data/tg-XX/*.parquet"
- config_name: "th-AI"
data_files:
- split: train
path: "data/th-AI/*.parquet"
- config_name: "th-AU"
data_files:
- split: train
path: "data/th-AU/*.parquet"
- config_name: "th-BE"
data_files:
- split: train
path: "data/th-BE/*.parquet"
- config_name: "th-BG"
data_files:
- split: train
path: "data/th-BG/*.parquet"
- config_name: "th-BR"
data_files:
- split: train
path: "data/th-BR/*.parquet"
- config_name: "th-BZ"
data_files:
- split: train
path: "data/th-BZ/*.parquet"
- config_name: "th-CA"
data_files:
- split: train
path: "data/th-CA/*.parquet"
- config_name: "th-CC"
data_files:
- split: train
path: "data/th-CC/*.parquet"
- config_name: "th-CH"
data_files:
- split: train
path: "data/th-CH/*.parquet"
- config_name: "th-CL"
data_files:
- split: train
path: "data/th-CL/*.parquet"
- config_name: "th-CN"
data_files:
- split: train
path: "data/th-CN/*.parquet"
- config_name: "th-CO"
data_files:
- split: train
path: "data/th-CO/*.parquet"
- config_name: "th-CZ"
data_files:
- split: train
path: "data/th-CZ/*.parquet"
- config_name: "th-DE"
data_files:
- split: train
path: "data/th-DE/*.parquet"
- config_name: "th-EN"
data_files:
- split: train
path: "data/th-EN/*.parquet"
- config_name: "th-ES"
data_files:
- split: train
path: "data/th-ES/*.parquet"
- config_name: "th-EU"
data_files:
- split: train
path: "data/th-EU/*.parquet"
- config_name: "th-FM"
data_files:
- split: train
path: "data/th-FM/*.parquet"
- config_name: "th-FR"
data_files:
- split: train
path: "data/th-FR/*.parquet"
- config_name: "th-GA"
data_files:
- split: train
path: "data/th-GA/*.parquet"
- config_name: "th-GB"
data_files:
- split: train
path: "data/th-GB/*.parquet"
- config_name: "th-GG"
data_files:
- split: train
path: "data/th-GG/*.parquet"
- config_name: "th-GR"
data_files:
- split: train
path: "data/th-GR/*.parquet"
- config_name: "th-HK"
data_files:
- split: train
path: "data/th-HK/*.parquet"
- config_name: "th-HU"
data_files:
- split: train
path: "data/th-HU/*.parquet"
- config_name: "th-ID"
data_files:
- split: train
path: "data/th-ID/*.parquet"
- config_name: "th-IM"
data_files:
- split: train
path: "data/th-IM/*.parquet"
- config_name: "th-IN"
data_files:
- split: train
path: "data/th-IN/*.parquet"
- config_name: "th-IO"
data_files:
- split: train
path: "data/th-IO/*.parquet"
- config_name: "th-IR"
data_files:
- split: train
path: "data/th-IR/*.parquet"
- config_name: "th-IS"
data_files:
- split: train
path: "data/th-IS/*.parquet"
- config_name: "th-IT"
data_files:
- split: train
path: "data/th-IT/*.parquet"
- config_name: "th-JP"
data_files:
- split: train
path: "data/th-JP/*.parquet"
- config_name: "th-KR"
data_files:
- split: train
path: "data/th-KR/*.parquet"
- config_name: "th-LA"
data_files:
- split: train
path: "data/th-LA/*.parquet"
- config_name: "th-LT"
data_files:
- split: train
path: "data/th-LT/*.parquet"
- config_name: "th-LV"
data_files:
- split: train
path: "data/th-LV/*.parquet"
- config_name: "th-ME"
data_files:
- split: train
path: "data/th-ME/*.parquet"
- config_name: "th-MH"
data_files:
- split: train
path: "data/th-MH/*.parquet"
- config_name: "th-ML"
data_files:
- split: train
path: "data/th-ML/*.parquet"
- config_name: "th-MN"
data_files:
- split: train
path: "data/th-MN/*.parquet"
- config_name: "th-MX"
data_files:
- split: train
path: "data/th-MX/*.parquet"
- config_name: "th-MY"
data_files:
- split: train
path: "data/th-MY/*.parquet"
- config_name: "th-NL"
data_files:
- split: train
path: "data/th-NL/*.parquet"
- config_name: "th-NO"
data_files:
- split: train
path: "data/th-NO/*.parquet"
- config_name: "th-NZ"
data_files:
- split: train
path: "data/th-NZ/*.parquet"
- config_name: "th-PE"
data_files:
- split: train
path: "data/th-PE/*.parquet"
- config_name: "th-PL"
data_files:
- split: train
path: "data/th-PL/*.parquet"
- config_name: "th-PS"
data_files:
- split: train
path: "data/th-PS/*.parquet"
- config_name: "th-PW"
data_files:
- split: train
path: "data/th-PW/*.parquet"
- config_name: "th-RO"
data_files:
- split: train
path: "data/th-RO/*.parquet"
- config_name: "th-RU"
data_files:
- split: train
path: "data/th-RU/*.parquet"
- config_name: "th-SE"
data_files:
- split: train
path: "data/th-SE/*.parquet"
- config_name: "th-SG"
data_files:
- split: train
path: "data/th-SG/*.parquet"
- config_name: "th-SH"
data_files:
- split: train
path: "data/th-SH/*.parquet"
- config_name: "th-TA"
data_files:
- split: train
path: "data/th-TA/*.parquet"
- config_name: "th-TH"
data_files:
- split: train
path: "data/th-TH/*.parquet"
- config_name: "th-TK"
data_files:
- split: train
path: "data/th-TK/*.parquet"
- config_name: "th-TL"
data_files:
- split: train
path: "data/th-TL/*.parquet"
- config_name: "th-TR"
data_files:
- split: train
path: "data/th-TR/*.parquet"
- config_name: "th-TV"
data_files:
- split: train
path: "data/th-TV/*.parquet"
- config_name: "th-TW"
data_files:
- split: train
path: "data/th-TW/*.parquet"
- config_name: "th-US"
data_files:
- split: train
path: "data/th-US/*.parquet"
- config_name: "th-VI"
data_files:
- split: train
path: "data/th-VI/*.parquet"
- config_name: "th-VN"
data_files:
- split: train
path: "data/th-VN/*.parquet"
- config_name: "th-VU"
data_files:
- split: train
path: "data/th-VU/*.parquet"
- config_name: "th-WS"
data_files:
- split: train
path: "data/th-WS/*.parquet"
- config_name: "th-XX"
data_files:
- split: train
path: "data/th-XX/*.parquet"
- config_name: "th-YT"
data_files:
- split: train
path: "data/th-YT/*.parquet"
- config_name: "th-ZA"
data_files:
- split: train
path: "data/th-ZA/*.parquet"
- config_name: "tk-GB"
data_files:
- split: train
path: "data/tk-GB/*.parquet"
- config_name: "tk-IS"
data_files:
- split: train
path: "data/tk-IS/*.parquet"
- config_name: "tk-TK"
data_files:
- split: train
path: "data/tk-TK/*.parquet"
- config_name: "tk-TM"
data_files:
- split: train
path: "data/tk-TM/*.parquet"
- config_name: "tk-TR"
data_files:
- split: train
path: "data/tk-TR/*.parquet"
- config_name: "tk-XX"
data_files:
- split: train
path: "data/tk-XX/*.parquet"
- config_name: "tl-AI"
data_files:
- split: train
path: "data/tl-AI/*.parquet"
- config_name: "tl-BE"
data_files:
- split: train
path: "data/tl-BE/*.parquet"
- config_name: "tl-BR"
data_files:
- split: train
path: "data/tl-BR/*.parquet"
- config_name: "tl-CA"
data_files:
- split: train
path: "data/tl-CA/*.parquet"
- config_name: "tl-CF"
data_files:
- split: train
path: "data/tl-CF/*.parquet"
- config_name: "tl-CN"
data_files:
- split: train
path: "data/tl-CN/*.parquet"
- config_name: "tl-CO"
data_files:
- split: train
path: "data/tl-CO/*.parquet"
- config_name: "tl-DE"
data_files:
- split: train
path: "data/tl-DE/*.parquet"
- config_name: "tl-DK"
data_files:
- split: train
path: "data/tl-DK/*.parquet"
- config_name: "tl-ES"
data_files:
- split: train
path: "data/tl-ES/*.parquet"
- config_name: "tl-EU"
data_files:
- split: train
path: "data/tl-EU/*.parquet"
- config_name: "tl-FM"
data_files:
- split: train
path: "data/tl-FM/*.parquet"
- config_name: "tl-FR"
data_files:
- split: train
path: "data/tl-FR/*.parquet"
- config_name: "tl-GB"
data_files:
- split: train
path: "data/tl-GB/*.parquet"
- config_name: "tl-IN"
data_files:
- split: train
path: "data/tl-IN/*.parquet"
- config_name: "tl-IO"
data_files:
- split: train
path: "data/tl-IO/*.parquet"
- config_name: "tl-IS"
data_files:
- split: train
path: "data/tl-IS/*.parquet"
- config_name: "tl-IT"
data_files:
- split: train
path: "data/tl-IT/*.parquet"
- config_name: "tl-NL"
data_files:
- split: train
path: "data/tl-NL/*.parquet"
- config_name: "tl-NU"
data_files:
- split: train
path: "data/tl-NU/*.parquet"
- config_name: "tl-PH"
data_files:
- split: train
path: "data/tl-PH/*.parquet"
- config_name: "tl-PK"
data_files:
- split: train
path: "data/tl-PK/*.parquet"
- config_name: "tl-PL"
data_files:
- split: train
path: "data/tl-PL/*.parquet"
- config_name: "tl-RU"
data_files:
- split: train
path: "data/tl-RU/*.parquet"
- config_name: "tl-TK"
data_files:
- split: train
path: "data/tl-TK/*.parquet"
- config_name: "tl-TL"
data_files:
- split: train
path: "data/tl-TL/*.parquet"
- config_name: "tl-TV"
data_files:
- split: train
path: "data/tl-TV/*.parquet"
- config_name: "tl-TW"
data_files:
- split: train
path: "data/tl-TW/*.parquet"
- config_name: "tl-UA"
data_files:
- split: train
path: "data/tl-UA/*.parquet"
- config_name: "tl-US"
data_files:
- split: train
path: "data/tl-US/*.parquet"
- config_name: "tl-VN"
data_files:
- split: train
path: "data/tl-VN/*.parquet"
- config_name: "tl-XX"
data_files:
- split: train
path: "data/tl-XX/*.parquet"
- config_name: "tr-AA"
data_files:
- split: train
path: "data/tr-AA/*.parquet"
- config_name: "tr-AE"
data_files:
- split: train
path: "data/tr-AE/*.parquet"
- config_name: "tr-AI"
data_files:
- split: train
path: "data/tr-AI/*.parquet"
- config_name: "tr-AL"
data_files:
- split: train
path: "data/tr-AL/*.parquet"
- config_name: "tr-AM"
data_files:
- split: train
path: "data/tr-AM/*.parquet"
- config_name: "tr-AR"
data_files:
- split: train
path: "data/tr-AR/*.parquet"
- config_name: "tr-AT"
data_files:
- split: train
path: "data/tr-AT/*.parquet"
- config_name: "tr-AU"
data_files:
- split: train
path: "data/tr-AU/*.parquet"
- config_name: "tr-AZ"
data_files:
- split: train
path: "data/tr-AZ/*.parquet"
- config_name: "tr-BA"
data_files:
- split: train
path: "data/tr-BA/*.parquet"
- config_name: "tr-BD"
data_files:
- split: train
path: "data/tr-BD/*.parquet"
- config_name: "tr-BE"
data_files:
- split: train
path: "data/tr-BE/*.parquet"
- config_name: "tr-BG"
data_files:
- split: train
path: "data/tr-BG/*.parquet"
- config_name: "tr-BO"
data_files:
- split: train
path: "data/tr-BO/*.parquet"
- config_name: "tr-BR"
data_files:
- split: train
path: "data/tr-BR/*.parquet"
- config_name: "tr-BZ"
data_files:
- split: train
path: "data/tr-BZ/*.parquet"
- config_name: "tr-CA"
data_files:
- split: train
path: "data/tr-CA/*.parquet"
- config_name: "tr-CC"
data_files:
- split: train
path: "data/tr-CC/*.parquet"
- config_name: "tr-CF"
data_files:
- split: train
path: "data/tr-CF/*.parquet"
- config_name: "tr-CH"
data_files:
- split: train
path: "data/tr-CH/*.parquet"
- config_name: "tr-CL"
data_files:
- split: train
path: "data/tr-CL/*.parquet"
- config_name: "tr-CN"
data_files:
- split: train
path: "data/tr-CN/*.parquet"
- config_name: "tr-CO"
data_files:
- split: train
path: "data/tr-CO/*.parquet"
- config_name: "tr-CX"
data_files:
- split: train
path: "data/tr-CX/*.parquet"
- config_name: "tr-CY"
data_files:
- split: train
path: "data/tr-CY/*.parquet"
- config_name: "tr-CZ"
data_files:
- split: train
path: "data/tr-CZ/*.parquet"
- config_name: "tr-DE"
data_files:
- split: train
path: "data/tr-DE/*.parquet"
- config_name: "tr-DJ"
data_files:
- split: train
path: "data/tr-DJ/*.parquet"
- config_name: "tr-DK"
data_files:
- split: train
path: "data/tr-DK/*.parquet"
- config_name: "tr-DO"
data_files:
- split: train
path: "data/tr-DO/*.parquet"
- config_name: "tr-EE"
data_files:
- split: train
path: "data/tr-EE/*.parquet"
- config_name: "tr-EG"
data_files:
- split: train
path: "data/tr-EG/*.parquet"
- config_name: "tr-EN"
data_files:
- split: train
path: "data/tr-EN/*.parquet"
- config_name: "tr-ES"
data_files:
- split: train
path: "data/tr-ES/*.parquet"
- config_name: "tr-EU"
data_files:
- split: train
path: "data/tr-EU/*.parquet"
- config_name: "tr-FI"
data_files:
- split: train
path: "data/tr-FI/*.parquet"
- config_name: "tr-FM"
data_files:
- split: train
path: "data/tr-FM/*.parquet"
- config_name: "tr-FR"
data_files:
- split: train
path: "data/tr-FR/*.parquet"
- config_name: "tr-GA"
data_files:
- split: train
path: "data/tr-GA/*.parquet"
- config_name: "tr-GB"
data_files:
- split: train
path: "data/tr-GB/*.parquet"
- config_name: "tr-GE"
data_files:
- split: train
path: "data/tr-GE/*.parquet"
- config_name: "tr-GG"
data_files:
- split: train
path: "data/tr-GG/*.parquet"
- config_name: "tr-GQ"
data_files:
- split: train
path: "data/tr-GQ/*.parquet"
- config_name: "tr-GR"
data_files:
- split: train
path: "data/tr-GR/*.parquet"
- config_name: "tr-HR"
data_files:
- split: train
path: "data/tr-HR/*.parquet"
- config_name: "tr-HU"
data_files:
- split: train
path: "data/tr-HU/*.parquet"
- config_name: "tr-ID"
data_files:
- split: train
path: "data/tr-ID/*.parquet"
- config_name: "tr-IE"
data_files:
- split: train
path: "data/tr-IE/*.parquet"
- config_name: "tr-IL"
data_files:
- split: train
path: "data/tr-IL/*.parquet"
- config_name: "tr-IM"
data_files:
- split: train
path: "data/tr-IM/*.parquet"
- config_name: "tr-IN"
data_files:
- split: train
path: "data/tr-IN/*.parquet"
- config_name: "tr-IO"
data_files:
- split: train
path: "data/tr-IO/*.parquet"
- config_name: "tr-IQ"
data_files:
- split: train
path: "data/tr-IQ/*.parquet"
- config_name: "tr-IR"
data_files:
- split: train
path: "data/tr-IR/*.parquet"
- config_name: "tr-IT"
data_files:
- split: train
path: "data/tr-IT/*.parquet"
- config_name: "tr-JP"
data_files:
- split: train
path: "data/tr-JP/*.parquet"
- config_name: "tr-KG"
data_files:
- split: train
path: "data/tr-KG/*.parquet"
- config_name: "tr-KR"
data_files:
- split: train
path: "data/tr-KR/*.parquet"
- config_name: "tr-KZ"
data_files:
- split: train
path: "data/tr-KZ/*.parquet"
- config_name: "tr-LA"
data_files:
- split: train
path: "data/tr-LA/*.parquet"
- config_name: "tr-LI"
data_files:
- split: train
path: "data/tr-LI/*.parquet"
- config_name: "tr-LT"
data_files:
- split: train
path: "data/tr-LT/*.parquet"
- config_name: "tr-LU"
data_files:
- split: train
path: "data/tr-LU/*.parquet"
- config_name: "tr-LV"
data_files:
- split: train
path: "data/tr-LV/*.parquet"
- config_name: "tr-LY"
data_files:
- split: train
path: "data/tr-LY/*.parquet"
- config_name: "tr-MA"
data_files:
- split: train
path: "data/tr-MA/*.parquet"
- config_name: "tr-ME"
data_files:
- split: train
path: "data/tr-ME/*.parquet"
- config_name: "tr-ML"
data_files:
- split: train
path: "data/tr-ML/*.parquet"
- config_name: "tr-MX"
data_files:
- split: train
path: "data/tr-MX/*.parquet"
- config_name: "tr-NL"
data_files:
- split: train
path: "data/tr-NL/*.parquet"
- config_name: "tr-NO"
data_files:
- split: train
path: "data/tr-NO/*.parquet"
- config_name: "tr-NU"
data_files:
- split: train
path: "data/tr-NU/*.parquet"
- config_name: "tr-PE"
data_files:
- split: train
path: "data/tr-PE/*.parquet"
- config_name: "tr-PL"
data_files:
- split: train
path: "data/tr-PL/*.parquet"
- config_name: "tr-PT"
data_files:
- split: train
path: "data/tr-PT/*.parquet"
- config_name: "tr-PW"
data_files:
- split: train
path: "data/tr-PW/*.parquet"
- config_name: "tr-RO"
data_files:
- split: train
path: "data/tr-RO/*.parquet"
- config_name: "tr-RS"
data_files:
- split: train
path: "data/tr-RS/*.parquet"
- config_name: "tr-RU"
data_files:
- split: train
path: "data/tr-RU/*.parquet"
- config_name: "tr-SA"
data_files:
- split: train
path: "data/tr-SA/*.parquet"
- config_name: "tr-SE"
data_files:
- split: train
path: "data/tr-SE/*.parquet"
- config_name: "tr-SG"
data_files:
- split: train
path: "data/tr-SG/*.parquet"
- config_name: "tr-SI"
data_files:
- split: train
path: "data/tr-SI/*.parquet"
- config_name: "tr-SK"
data_files:
- split: train
path: "data/tr-SK/*.parquet"
- config_name: "tr-ST"
data_files:
- split: train
path: "data/tr-ST/*.parquet"
- config_name: "tr-TC"
data_files:
- split: train
path: "data/tr-TC/*.parquet"
- config_name: "tr-TH"
data_files:
- split: train
path: "data/tr-TH/*.parquet"
- config_name: "tr-TK"
data_files:
- split: train
path: "data/tr-TK/*.parquet"
- config_name: "tr-TM"
data_files:
- split: train
path: "data/tr-TM/*.parquet"
- config_name: "tr-TR"
data_files:
- split: train
path: "data/tr-TR/*.parquet"
- config_name: "tr-TV"
data_files:
- split: train
path: "data/tr-TV/*.parquet"
- config_name: "tr-TW"
data_files:
- split: train
path: "data/tr-TW/*.parquet"
- config_name: "tr-UA"
data_files:
- split: train
path: "data/tr-UA/*.parquet"
- config_name: "tr-US"
data_files:
- split: train
path: "data/tr-US/*.parquet"
- config_name: "tr-UY"
data_files:
- split: train
path: "data/tr-UY/*.parquet"
- config_name: "tr-VE"
data_files:
- split: train
path: "data/tr-VE/*.parquet"
- config_name: "tr-VN"
data_files:
- split: train
path: "data/tr-VN/*.parquet"
- config_name: "tr-WS"
data_files:
- split: train
path: "data/tr-WS/*.parquet"
- config_name: "tr-XX"
data_files:
- split: train
path: "data/tr-XX/*.parquet"
- config_name: "tr-ZA"
data_files:
- split: train
path: "data/tr-ZA/*.parquet"
- config_name: "tt-RU"
data_files:
- split: train
path: "data/tt-RU/*.parquet"
- config_name: "tt-TR"
data_files:
- split: train
path: "data/tt-TR/*.parquet"
- config_name: "tt-TT"
data_files:
- split: train
path: "data/tt-TT/*.parquet"
- config_name: "tt-XX"
data_files:
- split: train
path: "data/tt-XX/*.parquet"
- config_name: "ug-CN"
data_files:
- split: train
path: "data/ug-CN/*.parquet"
- config_name: "ug-HK"
data_files:
- split: train
path: "data/ug-HK/*.parquet"
- config_name: "ug-KZ"
data_files:
- split: train
path: "data/ug-KZ/*.parquet"
- config_name: "ug-NO"
data_files:
- split: train
path: "data/ug-NO/*.parquet"
- config_name: "ug-RU"
data_files:
- split: train
path: "data/ug-RU/*.parquet"
- config_name: "ug-US"
data_files:
- split: train
path: "data/ug-US/*.parquet"
- config_name: "ug-XX"
data_files:
- split: train
path: "data/ug-XX/*.parquet"
- config_name: "uk-AE"
data_files:
- split: train
path: "data/uk-AE/*.parquet"
- config_name: "uk-AM"
data_files:
- split: train
path: "data/uk-AM/*.parquet"
- config_name: "uk-AT"
data_files:
- split: train
path: "data/uk-AT/*.parquet"
- config_name: "uk-AW"
data_files:
- split: train
path: "data/uk-AW/*.parquet"
- config_name: "uk-BG"
data_files:
- split: train
path: "data/uk-BG/*.parquet"
- config_name: "uk-BR"
data_files:
- split: train
path: "data/uk-BR/*.parquet"
- config_name: "uk-BY"
data_files:
- split: train
path: "data/uk-BY/*.parquet"
- config_name: "uk-CA"
data_files:
- split: train
path: "data/uk-CA/*.parquet"
- config_name: "uk-CC"
data_files:
- split: train
path: "data/uk-CC/*.parquet"
- config_name: "uk-CD"
data_files:
- split: train
path: "data/uk-CD/*.parquet"
- config_name: "uk-CF"
data_files:
- split: train
path: "data/uk-CF/*.parquet"
- config_name: "uk-CH"
data_files:
- split: train
path: "data/uk-CH/*.parquet"
- config_name: "uk-CN"
data_files:
- split: train
path: "data/uk-CN/*.parquet"
- config_name: "uk-CO"
data_files:
- split: train
path: "data/uk-CO/*.parquet"
- config_name: "uk-CZ"
data_files:
- split: train
path: "data/uk-CZ/*.parquet"
- config_name: "uk-DE"
data_files:
- split: train
path: "data/uk-DE/*.parquet"
- config_name: "uk-DK"
data_files:
- split: train
path: "data/uk-DK/*.parquet"
- config_name: "uk-EE"
data_files:
- split: train
path: "data/uk-EE/*.parquet"
- config_name: "uk-EN"
data_files:
- split: train
path: "data/uk-EN/*.parquet"
- config_name: "uk-ES"
data_files:
- split: train
path: "data/uk-ES/*.parquet"
- config_name: "uk-EU"
data_files:
- split: train
path: "data/uk-EU/*.parquet"
- config_name: "uk-FI"
data_files:
- split: train
path: "data/uk-FI/*.parquet"
- config_name: "uk-FM"
data_files:
- split: train
path: "data/uk-FM/*.parquet"
- config_name: "uk-FR"
data_files:
- split: train
path: "data/uk-FR/*.parquet"
- config_name: "uk-GA"
data_files:
- split: train
path: "data/uk-GA/*.parquet"
- config_name: "uk-GB"
data_files:
- split: train
path: "data/uk-GB/*.parquet"
- config_name: "uk-GE"
data_files:
- split: train
path: "data/uk-GE/*.parquet"
- config_name: "uk-GG"
data_files:
- split: train
path: "data/uk-GG/*.parquet"
- config_name: "uk-GQ"
data_files:
- split: train
path: "data/uk-GQ/*.parquet"
- config_name: "uk-GR"
data_files:
- split: train
path: "data/uk-GR/*.parquet"
- config_name: "uk-HR"
data_files:
- split: train
path: "data/uk-HR/*.parquet"
- config_name: "uk-HT"
data_files:
- split: train
path: "data/uk-HT/*.parquet"
- config_name: "uk-HU"
data_files:
- split: train
path: "data/uk-HU/*.parquet"
- config_name: "uk-ID"
data_files:
- split: train
path: "data/uk-ID/*.parquet"
- config_name: "uk-IE"
data_files:
- split: train
path: "data/uk-IE/*.parquet"
- config_name: "uk-IL"
data_files:
- split: train
path: "data/uk-IL/*.parquet"
- config_name: "uk-IN"
data_files:
- split: train
path: "data/uk-IN/*.parquet"
- config_name: "uk-IO"
data_files:
- split: train
path: "data/uk-IO/*.parquet"
- config_name: "uk-IS"
data_files:
- split: train
path: "data/uk-IS/*.parquet"
- config_name: "uk-IT"
data_files:
- split: train
path: "data/uk-IT/*.parquet"
- config_name: "uk-KG"
data_files:
- split: train
path: "data/uk-KG/*.parquet"
- config_name: "uk-KR"
data_files:
- split: train
path: "data/uk-KR/*.parquet"
- config_name: "uk-KZ"
data_files:
- split: train
path: "data/uk-KZ/*.parquet"
- config_name: "uk-LI"
data_files:
- split: train
path: "data/uk-LI/*.parquet"
- config_name: "uk-LM"
data_files:
- split: train
path: "data/uk-LM/*.parquet"
- config_name: "uk-LT"
data_files:
- split: train
path: "data/uk-LT/*.parquet"
- config_name: "uk-LV"
data_files:
- split: train
path: "data/uk-LV/*.parquet"
- config_name: "uk-MA"
data_files:
- split: train
path: "data/uk-MA/*.parquet"
- config_name: "uk-MD"
data_files:
- split: train
path: "data/uk-MD/*.parquet"
- config_name: "uk-ME"
data_files:
- split: train
path: "data/uk-ME/*.parquet"
- config_name: "uk-ML"
data_files:
- split: train
path: "data/uk-ML/*.parquet"
- config_name: "uk-MX"
data_files:
- split: train
path: "data/uk-MX/*.parquet"
- config_name: "uk-NL"
data_files:
- split: train
path: "data/uk-NL/*.parquet"
- config_name: "uk-PL"
data_files:
- split: train
path: "data/uk-PL/*.parquet"
- config_name: "uk-PM"
data_files:
- split: train
path: "data/uk-PM/*.parquet"
- config_name: "uk-PN"
data_files:
- split: train
path: "data/uk-PN/*.parquet"
- config_name: "uk-PT"
data_files:
- split: train
path: "data/uk-PT/*.parquet"
- config_name: "uk-RO"
data_files:
- split: train
path: "data/uk-RO/*.parquet"
- config_name: "uk-RS"
data_files:
- split: train
path: "data/uk-RS/*.parquet"
- config_name: "uk-RU"
data_files:
- split: train
path: "data/uk-RU/*.parquet"
- config_name: "uk-SE"
data_files:
- split: train
path: "data/uk-SE/*.parquet"
- config_name: "uk-SK"
data_files:
- split: train
path: "data/uk-SK/*.parquet"
- config_name: "uk-TH"
data_files:
- split: train
path: "data/uk-TH/*.parquet"
- config_name: "uk-TK"
data_files:
- split: train
path: "data/uk-TK/*.parquet"
- config_name: "uk-TO"
data_files:
- split: train
path: "data/uk-TO/*.parquet"
- config_name: "uk-TR"
data_files:
- split: train
path: "data/uk-TR/*.parquet"
- config_name: "uk-TV"
data_files:
- split: train
path: "data/uk-TV/*.parquet"
- config_name: "uk-TW"
data_files:
- split: train
path: "data/uk-TW/*.parquet"
- config_name: "uk-UA"
data_files:
- split: train
path: "data/uk-UA/*.parquet"
- config_name: "uk-UK"
data_files:
- split: train
path: "data/uk-UK/*.parquet"
- config_name: "uk-US"
data_files:
- split: train
path: "data/uk-US/*.parquet"
- config_name: "uk-UY"
data_files:
- split: train
path: "data/uk-UY/*.parquet"
- config_name: "uk-UZ"
data_files:
- split: train
path: "data/uk-UZ/*.parquet"
- config_name: "uk-VA"
data_files:
- split: train
path: "data/uk-VA/*.parquet"
- config_name: "uk-VC"
data_files:
- split: train
path: "data/uk-VC/*.parquet"
- config_name: "uk-VG"
data_files:
- split: train
path: "data/uk-VG/*.parquet"
- config_name: "uk-WS"
data_files:
- split: train
path: "data/uk-WS/*.parquet"
- config_name: "uk-XX"
data_files:
- split: train
path: "data/uk-XX/*.parquet"
- config_name: "uk-ZA"
data_files:
- split: train
path: "data/uk-ZA/*.parquet"
- config_name: "ur-AA"
data_files:
- split: train
path: "data/ur-AA/*.parquet"
- config_name: "ur-AE"
data_files:
- split: train
path: "data/ur-AE/*.parquet"
- config_name: "ur-AU"
data_files:
- split: train
path: "data/ur-AU/*.parquet"
- config_name: "ur-CA"
data_files:
- split: train
path: "data/ur-CA/*.parquet"
- config_name: "ur-CN"
data_files:
- split: train
path: "data/ur-CN/*.parquet"
- config_name: "ur-CO"
data_files:
- split: train
path: "data/ur-CO/*.parquet"
- config_name: "ur-DE"
data_files:
- split: train
path: "data/ur-DE/*.parquet"
- config_name: "ur-ES"
data_files:
- split: train
path: "data/ur-ES/*.parquet"
- config_name: "ur-EU"
data_files:
- split: train
path: "data/ur-EU/*.parquet"
- config_name: "ur-GB"
data_files:
- split: train
path: "data/ur-GB/*.parquet"
- config_name: "ur-IN"
data_files:
- split: train
path: "data/ur-IN/*.parquet"
- config_name: "ur-IQ"
data_files:
- split: train
path: "data/ur-IQ/*.parquet"
- config_name: "ur-IR"
data_files:
- split: train
path: "data/ur-IR/*.parquet"
- config_name: "ur-LB"
data_files:
- split: train
path: "data/ur-LB/*.parquet"
- config_name: "ur-LT"
data_files:
- split: train
path: "data/ur-LT/*.parquet"
- config_name: "ur-NL"
data_files:
- split: train
path: "data/ur-NL/*.parquet"
- config_name: "ur-NO"
data_files:
- split: train
path: "data/ur-NO/*.parquet"
- config_name: "ur-PK"
data_files:
- split: train
path: "data/ur-PK/*.parquet"
- config_name: "ur-PL"
data_files:
- split: train
path: "data/ur-PL/*.parquet"
- config_name: "ur-PT"
data_files:
- split: train
path: "data/ur-PT/*.parquet"
- config_name: "ur-RU"
data_files:
- split: train
path: "data/ur-RU/*.parquet"
- config_name: "ur-SA"
data_files:
- split: train
path: "data/ur-SA/*.parquet"
- config_name: "ur-TK"
data_files:
- split: train
path: "data/ur-TK/*.parquet"
- config_name: "ur-TR"
data_files:
- split: train
path: "data/ur-TR/*.parquet"
- config_name: "ur-TV"
data_files:
- split: train
path: "data/ur-TV/*.parquet"
- config_name: "ur-UR"
data_files:
- split: train
path: "data/ur-UR/*.parquet"
- config_name: "ur-US"
data_files:
- split: train
path: "data/ur-US/*.parquet"
- config_name: "ur-UZ"
data_files:
- split: train
path: "data/ur-UZ/*.parquet"
- config_name: "ur-XX"
data_files:
- split: train
path: "data/ur-XX/*.parquet"
- config_name: "uz-RU"
data_files:
- split: train
path: "data/uz-RU/*.parquet"
- config_name: "uz-TR"
data_files:
- split: train
path: "data/uz-TR/*.parquet"
- config_name: "uz-US"
data_files:
- split: train
path: "data/uz-US/*.parquet"
- config_name: "uz-UZ"
data_files:
- split: train
path: "data/uz-UZ/*.parquet"
- config_name: "uz-XX"
data_files:
- split: train
path: "data/uz-XX/*.parquet"
- config_name: "vi-AD"
data_files:
- split: train
path: "data/vi-AD/*.parquet"
- config_name: "vi-AE"
data_files:
- split: train
path: "data/vi-AE/*.parquet"
- config_name: "vi-AG"
data_files:
- split: train
path: "data/vi-AG/*.parquet"
- config_name: "vi-AI"
data_files:
- split: train
path: "data/vi-AI/*.parquet"
- config_name: "vi-AM"
data_files:
- split: train
path: "data/vi-AM/*.parquet"
- config_name: "vi-AR"
data_files:
- split: train
path: "data/vi-AR/*.parquet"
- config_name: "vi-AU"
data_files:
- split: train
path: "data/vi-AU/*.parquet"
- config_name: "vi-BE"
data_files:
- split: train
path: "data/vi-BE/*.parquet"
- config_name: "vi-BR"
data_files:
- split: train
path: "data/vi-BR/*.parquet"
- config_name: "vi-BZ"
data_files:
- split: train
path: "data/vi-BZ/*.parquet"
- config_name: "vi-CA"
data_files:
- split: train
path: "data/vi-CA/*.parquet"
- config_name: "vi-CC"
data_files:
- split: train
path: "data/vi-CC/*.parquet"
- config_name: "vi-CF"
data_files:
- split: train
path: "data/vi-CF/*.parquet"
- config_name: "vi-CH"
data_files:
- split: train
path: "data/vi-CH/*.parquet"
- config_name: "vi-CN"
data_files:
- split: train
path: "data/vi-CN/*.parquet"
- config_name: "vi-CO"
data_files:
- split: train
path: "data/vi-CO/*.parquet"
- config_name: "vi-CX"
data_files:
- split: train
path: "data/vi-CX/*.parquet"
- config_name: "vi-CY"
data_files:
- split: train
path: "data/vi-CY/*.parquet"
- config_name: "vi-CZ"
data_files:
- split: train
path: "data/vi-CZ/*.parquet"
- config_name: "vi-DE"
data_files:
- split: train
path: "data/vi-DE/*.parquet"
- config_name: "vi-DK"
data_files:
- split: train
path: "data/vi-DK/*.parquet"
- config_name: "vi-DO"
data_files:
- split: train
path: "data/vi-DO/*.parquet"
- config_name: "vi-EC"
data_files:
- split: train
path: "data/vi-EC/*.parquet"
- config_name: "vi-EN"
data_files:
- split: train
path: "data/vi-EN/*.parquet"
- config_name: "vi-ES"
data_files:
- split: train
path: "data/vi-ES/*.parquet"
- config_name: "vi-EU"
data_files:
- split: train
path: "data/vi-EU/*.parquet"
- config_name: "vi-FI"
data_files:
- split: train
path: "data/vi-FI/*.parquet"
- config_name: "vi-FM"
data_files:
- split: train
path: "data/vi-FM/*.parquet"
- config_name: "vi-FR"
data_files:
- split: train
path: "data/vi-FR/*.parquet"
- config_name: "vi-GA"
data_files:
- split: train
path: "data/vi-GA/*.parquet"
- config_name: "vi-GB"
data_files:
- split: train
path: "data/vi-GB/*.parquet"
- config_name: "vi-GG"
data_files:
- split: train
path: "data/vi-GG/*.parquet"
- config_name: "vi-GO"
data_files:
- split: train
path: "data/vi-GO/*.parquet"
- config_name: "vi-GQ"
data_files:
- split: train
path: "data/vi-GQ/*.parquet"
- config_name: "vi-GR"
data_files:
- split: train
path: "data/vi-GR/*.parquet"
- config_name: "vi-HK"
data_files:
- split: train
path: "data/vi-HK/*.parquet"
- config_name: "vi-HU"
data_files:
- split: train
path: "data/vi-HU/*.parquet"
- config_name: "vi-ID"
data_files:
- split: train
path: "data/vi-ID/*.parquet"
- config_name: "vi-IE"
data_files:
- split: train
path: "data/vi-IE/*.parquet"
- config_name: "vi-IL"
data_files:
- split: train
path: "data/vi-IL/*.parquet"
- config_name: "vi-IM"
data_files:
- split: train
path: "data/vi-IM/*.parquet"
- config_name: "vi-IN"
data_files:
- split: train
path: "data/vi-IN/*.parquet"
- config_name: "vi-IO"
data_files:
- split: train
path: "data/vi-IO/*.parquet"
- config_name: "vi-IR"
data_files:
- split: train
path: "data/vi-IR/*.parquet"
- config_name: "vi-IS"
data_files:
- split: train
path: "data/vi-IS/*.parquet"
- config_name: "vi-IT"
data_files:
- split: train
path: "data/vi-IT/*.parquet"
- config_name: "vi-JP"
data_files:
- split: train
path: "data/vi-JP/*.parquet"
- config_name: "vi-KR"
data_files:
- split: train
path: "data/vi-KR/*.parquet"
- config_name: "vi-KY"
data_files:
- split: train
path: "data/vi-KY/*.parquet"
- config_name: "vi-LA"
data_files:
- split: train
path: "data/vi-LA/*.parquet"
- config_name: "vi-LI"
data_files:
- split: train
path: "data/vi-LI/*.parquet"
- config_name: "vi-LT"
data_files:
- split: train
path: "data/vi-LT/*.parquet"
- config_name: "vi-LU"
data_files:
- split: train
path: "data/vi-LU/*.parquet"
- config_name: "vi-LY"
data_files:
- split: train
path: "data/vi-LY/*.parquet"
- config_name: "vi-ME"
data_files:
- split: train
path: "data/vi-ME/*.parquet"
- config_name: "vi-ML"
data_files:
- split: train
path: "data/vi-ML/*.parquet"
- config_name: "vi-MM"
data_files:
- split: train
path: "data/vi-MM/*.parquet"
- config_name: "vi-MX"
data_files:
- split: train
path: "data/vi-MX/*.parquet"
- config_name: "vi-MY"
data_files:
- split: train
path: "data/vi-MY/*.parquet"
- config_name: "vi-NG"
data_files:
- split: train
path: "data/vi-NG/*.parquet"
- config_name: "vi-NL"
data_files:
- split: train
path: "data/vi-NL/*.parquet"
- config_name: "vi-NO"
data_files:
- split: train
path: "data/vi-NO/*.parquet"
- config_name: "vi-NZ"
data_files:
- split: train
path: "data/vi-NZ/*.parquet"
- config_name: "vi-PE"
data_files:
- split: train
path: "data/vi-PE/*.parquet"
- config_name: "vi-PH"
data_files:
- split: train
path: "data/vi-PH/*.parquet"
- config_name: "vi-PL"
data_files:
- split: train
path: "data/vi-PL/*.parquet"
- config_name: "vi-PT"
data_files:
- split: train
path: "data/vi-PT/*.parquet"
- config_name: "vi-PW"
data_files:
- split: train
path: "data/vi-PW/*.parquet"
- config_name: "vi-RE"
data_files:
- split: train
path: "data/vi-RE/*.parquet"
- config_name: "vi-RO"
data_files:
- split: train
path: "data/vi-RO/*.parquet"
- config_name: "vi-RU"
data_files:
- split: train
path: "data/vi-RU/*.parquet"
- config_name: "vi-SA"
data_files:
- split: train
path: "data/vi-SA/*.parquet"
- config_name: "vi-SE"
data_files:
- split: train
path: "data/vi-SE/*.parquet"
- config_name: "vi-SG"
data_files:
- split: train
path: "data/vi-SG/*.parquet"
- config_name: "vi-SH"
data_files:
- split: train
path: "data/vi-SH/*.parquet"
- config_name: "vi-SK"
data_files:
- split: train
path: "data/vi-SK/*.parquet"
- config_name: "vi-SO"
data_files:
- split: train
path: "data/vi-SO/*.parquet"
- config_name: "vi-ST"
data_files:
- split: train
path: "data/vi-ST/*.parquet"
- config_name: "vi-TH"
data_files:
- split: train
path: "data/vi-TH/*.parquet"
- config_name: "vi-TK"
data_files:
- split: train
path: "data/vi-TK/*.parquet"
- config_name: "vi-TL"
data_files:
- split: train
path: "data/vi-TL/*.parquet"
- config_name: "vi-TO"
data_files:
- split: train
path: "data/vi-TO/*.parquet"
- config_name: "vi-TR"
data_files:
- split: train
path: "data/vi-TR/*.parquet"
- config_name: "vi-TV"
data_files:
- split: train
path: "data/vi-TV/*.parquet"
- config_name: "vi-TW"
data_files:
- split: train
path: "data/vi-TW/*.parquet"
- config_name: "vi-UA"
data_files:
- split: train
path: "data/vi-UA/*.parquet"
- config_name: "vi-UK"
data_files:
- split: train
path: "data/vi-UK/*.parquet"
- config_name: "vi-US"
data_files:
- split: train
path: "data/vi-US/*.parquet"
- config_name: "vi-VA"
data_files:
- split: train
path: "data/vi-VA/*.parquet"
- config_name: "vi-VC"
data_files:
- split: train
path: "data/vi-VC/*.parquet"
- config_name: "vi-VE"
data_files:
- split: train
path: "data/vi-VE/*.parquet"
- config_name: "vi-VI"
data_files:
- split: train
path: "data/vi-VI/*.parquet"
- config_name: "vi-VN"
data_files:
- split: train
path: "data/vi-VN/*.parquet"
- config_name: "vi-WS"
data_files:
- split: train
path: "data/vi-WS/*.parquet"
- config_name: "vi-XX"
data_files:
- split: train
path: "data/vi-XX/*.parquet"
- config_name: "vi-ZA"
data_files:
- split: train
path: "data/vi-ZA/*.parquet"
- config_name: "vo-XX"
data_files:
- split: train
path: "data/vo-XX/*.parquet"
- config_name: "wa-XX"
data_files:
- split: train
path: "data/wa-XX/*.parquet"
- config_name: "war-IS"
data_files:
- split: train
path: "data/war-IS/*.parquet"
- config_name: "war-XX"
data_files:
- split: train
path: "data/war-XX/*.parquet"
- config_name: "xal-IS"
data_files:
- split: train
path: "data/xal-IS/*.parquet"
- config_name: "xmf-XX"
data_files:
- split: train
path: "data/xmf-XX/*.parquet"
- config_name: "yi-CO"
data_files:
- split: train
path: "data/yi-CO/*.parquet"
- config_name: "yi-DE"
data_files:
- split: train
path: "data/yi-DE/*.parquet"
- config_name: "yi-IL"
data_files:
- split: train
path: "data/yi-IL/*.parquet"
- config_name: "yi-JP"
data_files:
- split: train
path: "data/yi-JP/*.parquet"
- config_name: "yi-RU"
data_files:
- split: train
path: "data/yi-RU/*.parquet"
- config_name: "yi-US"
data_files:
- split: train
path: "data/yi-US/*.parquet"
- config_name: "yi-XX"
data_files:
- split: train
path: "data/yi-XX/*.parquet"
- config_name: "yo-NG"
data_files:
- split: train
path: "data/yo-NG/*.parquet"
- config_name: "yo-XX"
data_files:
- split: train
path: "data/yo-XX/*.parquet"
- config_name: "zh-AE"
data_files:
- split: train
path: "data/zh-AE/*.parquet"
- config_name: "zh-AI"
data_files:
- split: train
path: "data/zh-AI/*.parquet"
- config_name: "zh-AL"
data_files:
- split: train
path: "data/zh-AL/*.parquet"
- config_name: "zh-AM"
data_files:
- split: train
path: "data/zh-AM/*.parquet"
- config_name: "zh-AR"
data_files:
- split: train
path: "data/zh-AR/*.parquet"
- config_name: "zh-AT"
data_files:
- split: train
path: "data/zh-AT/*.parquet"
- config_name: "zh-AU"
data_files:
- split: train
path: "data/zh-AU/*.parquet"
- config_name: "zh-BD"
data_files:
- split: train
path: "data/zh-BD/*.parquet"
- config_name: "zh-BR"
data_files:
- split: train
path: "data/zh-BR/*.parquet"
- config_name: "zh-BY"
data_files:
- split: train
path: "data/zh-BY/*.parquet"
- config_name: "zh-BZ"
data_files:
- split: train
path: "data/zh-BZ/*.parquet"
- config_name: "zh-CA"
data_files:
- split: train
path: "data/zh-CA/*.parquet"
- config_name: "zh-CC"
data_files:
- split: train
path: "data/zh-CC/*.parquet"
- config_name: "zh-CD"
data_files:
- split: train
path: "data/zh-CD/*.parquet"
- config_name: "zh-CF"
data_files:
- split: train
path: "data/zh-CF/*.parquet"
- config_name: "zh-CH"
data_files:
- split: train
path: "data/zh-CH/*.parquet"
- config_name: "zh-CI"
data_files:
- split: train
path: "data/zh-CI/*.parquet"
- config_name: "zh-CL"
data_files:
- split: train
path: "data/zh-CL/*.parquet"
- config_name: "zh-CM"
data_files:
- split: train
path: "data/zh-CM/*.parquet"
- config_name: "zh-CN"
data_files:
- split: train
path: "data/zh-CN/*.parquet"
- config_name: "zh-CO"
data_files:
- split: train
path: "data/zh-CO/*.parquet"
- config_name: "zh-CX"
data_files:
- split: train
path: "data/zh-CX/*.parquet"
- config_name: "zh-CY"
data_files:
- split: train
path: "data/zh-CY/*.parquet"
- config_name: "zh-CZ"
data_files:
- split: train
path: "data/zh-CZ/*.parquet"
- config_name: "zh-DE"
data_files:
- split: train
path: "data/zh-DE/*.parquet"
- config_name: "zh-DJ"
data_files:
- split: train
path: "data/zh-DJ/*.parquet"
- config_name: "zh-DK"
data_files:
- split: train
path: "data/zh-DK/*.parquet"
- config_name: "zh-DO"
data_files:
- split: train
path: "data/zh-DO/*.parquet"
- config_name: "zh-EE"
data_files:
- split: train
path: "data/zh-EE/*.parquet"
- config_name: "zh-EN"
data_files:
- split: train
path: "data/zh-EN/*.parquet"
- config_name: "zh-ES"
data_files:
- split: train
path: "data/zh-ES/*.parquet"
- config_name: "zh-EU"
data_files:
- split: train
path: "data/zh-EU/*.parquet"
- config_name: "zh-FI"
data_files:
- split: train
path: "data/zh-FI/*.parquet"
- config_name: "zh-FM"
data_files:
- split: train
path: "data/zh-FM/*.parquet"
- config_name: "zh-FR"
data_files:
- split: train
path: "data/zh-FR/*.parquet"
- config_name: "zh-GA"
data_files:
- split: train
path: "data/zh-GA/*.parquet"
- config_name: "zh-GB"
data_files:
- split: train
path: "data/zh-GB/*.parquet"
- config_name: "zh-GE"
data_files:
- split: train
path: "data/zh-GE/*.parquet"
- config_name: "zh-GG"
data_files:
- split: train
path: "data/zh-GG/*.parquet"
- config_name: "zh-GL"
data_files:
- split: train
path: "data/zh-GL/*.parquet"
- config_name: "zh-GQ"
data_files:
- split: train
path: "data/zh-GQ/*.parquet"
- config_name: "zh-GR"
data_files:
- split: train
path: "data/zh-GR/*.parquet"
- config_name: "zh-HK"
data_files:
- split: train
path: "data/zh-HK/*.parquet"
- config_name: "zh-HN"
data_files:
- split: train
path: "data/zh-HN/*.parquet"
- config_name: "zh-HR"
data_files:
- split: train
path: "data/zh-HR/*.parquet"
- config_name: "zh-HU"
data_files:
- split: train
path: "data/zh-HU/*.parquet"
- config_name: "zh-ID"
data_files:
- split: train
path: "data/zh-ID/*.parquet"
- config_name: "zh-IE"
data_files:
- split: train
path: "data/zh-IE/*.parquet"
- config_name: "zh-IL"
data_files:
- split: train
path: "data/zh-IL/*.parquet"
- config_name: "zh-IM"
data_files:
- split: train
path: "data/zh-IM/*.parquet"
- config_name: "zh-IN"
data_files:
- split: train
path: "data/zh-IN/*.parquet"
- config_name: "zh-IO"
data_files:
- split: train
path: "data/zh-IO/*.parquet"
- config_name: "zh-IR"
data_files:
- split: train
path: "data/zh-IR/*.parquet"
- config_name: "zh-IS"
data_files:
- split: train
path: "data/zh-IS/*.parquet"
- config_name: "zh-IT"
data_files:
- split: train
path: "data/zh-IT/*.parquet"
- config_name: "zh-JP"
data_files:
- split: train
path: "data/zh-JP/*.parquet"
- config_name: "zh-KE"
data_files:
- split: train
path: "data/zh-KE/*.parquet"
- config_name: "zh-KP"
data_files:
- split: train
path: "data/zh-KP/*.parquet"
- config_name: "zh-KR"
data_files:
- split: train
path: "data/zh-KR/*.parquet"
- config_name: "zh-KZ"
data_files:
- split: train
path: "data/zh-KZ/*.parquet"
- config_name: "zh-LA"
data_files:
- split: train
path: "data/zh-LA/*.parquet"
- config_name: "zh-LC"
data_files:
- split: train
path: "data/zh-LC/*.parquet"
- config_name: "zh-LI"
data_files:
- split: train
path: "data/zh-LI/*.parquet"
- config_name: "zh-LT"
data_files:
- split: train
path: "data/zh-LT/*.parquet"
- config_name: "zh-LU"
data_files:
- split: train
path: "data/zh-LU/*.parquet"
- config_name: "zh-LY"
data_files:
- split: train
path: "data/zh-LY/*.parquet"
- config_name: "zh-MA"
data_files:
- split: train
path: "data/zh-MA/*.parquet"
- config_name: "zh-ME"
data_files:
- split: train
path: "data/zh-ME/*.parquet"
- config_name: "zh-MG"
data_files:
- split: train
path: "data/zh-MG/*.parquet"
- config_name: "zh-MK"
data_files:
- split: train
path: "data/zh-MK/*.parquet"
- config_name: "zh-ML"
data_files:
- split: train
path: "data/zh-ML/*.parquet"
- config_name: "zh-MM"
data_files:
- split: train
path: "data/zh-MM/*.parquet"
- config_name: "zh-MN"
data_files:
- split: train
path: "data/zh-MN/*.parquet"
- config_name: "zh-MO"
data_files:
- split: train
path: "data/zh-MO/*.parquet"
- config_name: "zh-MU"
data_files:
- split: train
path: "data/zh-MU/*.parquet"
- config_name: "zh-MX"
data_files:
- split: train
path: "data/zh-MX/*.parquet"
- config_name: "zh-MY"
data_files:
- split: train
path: "data/zh-MY/*.parquet"
- config_name: "zh-NG"
data_files:
- split: train
path: "data/zh-NG/*.parquet"
- config_name: "zh-NL"
data_files:
- split: train
path: "data/zh-NL/*.parquet"
- config_name: "zh-NO"
data_files:
- split: train
path: "data/zh-NO/*.parquet"
- config_name: "zh-NZ"
data_files:
- split: train
path: "data/zh-NZ/*.parquet"
- config_name: "zh-PE"
data_files:
- split: train
path: "data/zh-PE/*.parquet"
- config_name: "zh-PH"
data_files:
- split: train
path: "data/zh-PH/*.parquet"
- config_name: "zh-PL"
data_files:
- split: train
path: "data/zh-PL/*.parquet"
- config_name: "zh-PM"
data_files:
- split: train
path: "data/zh-PM/*.parquet"
- config_name: "zh-PT"
data_files:
- split: train
path: "data/zh-PT/*.parquet"
- config_name: "zh-PW"
data_files:
- split: train
path: "data/zh-PW/*.parquet"
- config_name: "zh-QA"
data_files:
- split: train
path: "data/zh-QA/*.parquet"
- config_name: "zh-RO"
data_files:
- split: train
path: "data/zh-RO/*.parquet"
- config_name: "zh-RU"
data_files:
- split: train
path: "data/zh-RU/*.parquet"
- config_name: "zh-SB"
data_files:
- split: train
path: "data/zh-SB/*.parquet"
- config_name: "zh-SC"
data_files:
- split: train
path: "data/zh-SC/*.parquet"
- config_name: "zh-SE"
data_files:
- split: train
path: "data/zh-SE/*.parquet"
- config_name: "zh-SG"
data_files:
- split: train
path: "data/zh-SG/*.parquet"
- config_name: "zh-SH"
data_files:
- split: train
path: "data/zh-SH/*.parquet"
- config_name: "zh-SK"
data_files:
- split: train
path: "data/zh-SK/*.parquet"
- config_name: "zh-SO"
data_files:
- split: train
path: "data/zh-SO/*.parquet"
- config_name: "zh-TC"
data_files:
- split: train
path: "data/zh-TC/*.parquet"
- config_name: "zh-TH"
data_files:
- split: train
path: "data/zh-TH/*.parquet"
- config_name: "zh-TK"
data_files:
- split: train
path: "data/zh-TK/*.parquet"
- config_name: "zh-TM"
data_files:
- split: train
path: "data/zh-TM/*.parquet"
- config_name: "zh-TO"
data_files:
- split: train
path: "data/zh-TO/*.parquet"
- config_name: "zh-TR"
data_files:
- split: train
path: "data/zh-TR/*.parquet"
- config_name: "zh-TT"
data_files:
- split: train
path: "data/zh-TT/*.parquet"
- config_name: "zh-TV"
data_files:
- split: train
path: "data/zh-TV/*.parquet"
- config_name: "zh-TW"
data_files:
- split: train
path: "data/zh-TW/*.parquet"
- config_name: "zh-UA"
data_files:
- split: train
path: "data/zh-UA/*.parquet"
- config_name: "zh-UK"
data_files:
- split: train
path: "data/zh-UK/*.parquet"
- config_name: "zh-US"
data_files:
- split: train
path: "data/zh-US/*.parquet"
- config_name: "zh-VA"
data_files:
- split: train
path: "data/zh-VA/*.parquet"
- config_name: "zh-VC"
data_files:
- split: train
path: "data/zh-VC/*.parquet"
- config_name: "zh-VG"
data_files:
- split: train
path: "data/zh-VG/*.parquet"
- config_name: "zh-VN"
data_files:
- split: train
path: "data/zh-VN/*.parquet"
- config_name: "zh-WS"
data_files:
- split: train
path: "data/zh-WS/*.parquet"
- config_name: "zh-XX"
data_files:
- split: train
path: "data/zh-XX/*.parquet"
- config_name: "zh-ZA"
data_files:
- split: train
path: "data/zh-ZA/*.parquet"
- config_name: "zh-ZH"
data_files:
- split: train
path: "data/zh-ZH/*.parquet"
- config_name: "zh-ZN"
data_files:
- split: train
path: "data/zh-ZN/*.parquet"
- config_name: "all"
data_files:
- split: train
path: "data/**/*.parquet"
default: true
---

# Common Crawl Regional Corpus

A multilingual web corpus with geographic region annotations, extracted from
Common Crawl. Each document is labeled with a **locale** (language-region pair).

## Quick Start

```python
from datasets import load_dataset

# Load a specific locale
ds = load_dataset("Yusser/CC-LARD", "es-MX")

# Load all data
ds = load_dataset("Yusser/CC-LARD", "all")

# Access the data
for row in ds["train"]:
print(row["text"][:100], row["locale"], row["region_source"])
```

## Dataset Statistics

- **Total documents**: 13,150,911
- **Languages**: 140
- **Regions**: 349
- **Locales**: 4334

## Columns

| Column | Type | Description |
|--------|------|-------------|
| `text` | string | Document text |
| `lang` | string | ISO 639-1 language code |
| `region` | string | ISO 3166-1 alpha-2 region code |
| `locale` | string | Combined lang-region (e.g., es-MX) |
| `url` | string | Source URL |
| `lang_confidence` | float | fastText LID confidence |
| `region_source` | string | Signal used: html_lang, http_header, tld, none |
| `warc_date` | string | Crawl timestamp |
| `text_length` | int | Character count |
| `title` | string | Page title |
| `text_hash` | string | SHA-256 of normalized text |

## Available Locales

4334 locales across 140 languages.

## License

Derived from Common Crawl data, released under CC-BY-4.0.