wecover/OPUS_TED2020

---
configs:
- config_name: default
data_files:
- split: train
path: '*/*/train.parquet'
- split: valid
path: '*/*/valid.parquet'
- split: test
path: '*/*/test.parquet'
- config_name: af
data_files:
- split: train
path: '*/*af*/train.parquet'
- split: test
path: '*/*af*/test.parquet'
- split: valid
path: '*/*af*/valid.parquet'
- config_name: am
data_files:
- split: train
path: '*/*am*/train.parquet'
- split: test
path: '*/*am*/test.parquet'
- split: valid
path: '*/*am*/valid.parquet'
- config_name: ar
data_files:
- split: train
path: '*/*ar*/train.parquet'
- split: test
path: '*/*ar*/test.parquet'
- split: valid
path: '*/*ar*/valid.parquet'
- config_name: az
data_files:
- split: train
path: '*/*az*/train.parquet'
- split: test
path: '*/*az*/test.parquet'
- split: valid
path: '*/*az*/valid.parquet'
- config_name: be
data_files:
- split: train
path: '*/*be*/train.parquet'
- split: test
path: '*/*be*/test.parquet'
- split: valid
path: '*/*be*/valid.parquet'
- config_name: bg
data_files:
- split: train
path: '*/*bg*/train.parquet'
- split: test
path: '*/*bg*/test.parquet'
- split: valid
path: '*/*bg*/valid.parquet'
- config_name: bn
data_files:
- split: train
path: '*/*bn*/train.parquet'
- split: test
path: '*/*bn*/test.parquet'
- split: valid
path: '*/*bn*/valid.parquet'
- config_name: bs
data_files:
- split: train
path: '*/*bs*/train.parquet'
- split: test
path: '*/*bs*/test.parquet'
- split: valid
path: '*/*bs*/valid.parquet'
- config_name: ca
data_files:
- split: train
path: '*/*ca*/train.parquet'
- split: test
path: '*/*ca*/test.parquet'
- split: valid
path: '*/*ca*/valid.parquet'
- config_name: cs
data_files:
- split: train
path: '*/*cs*/train.parquet'
- split: test
path: '*/*cs*/test.parquet'
- split: valid
path: '*/*cs*/valid.parquet'
- config_name: da
data_files:
- split: train
path: '*/*da*/train.parquet'
- split: test
path: '*/*da*/test.parquet'
- split: valid
path: '*/*da*/valid.parquet'
- config_name: de
data_files:
- split: train
path: '*/*de*/train.parquet'
- split: test
path: '*/*de*/test.parquet'
- split: valid
path: '*/*de*/valid.parquet'
- config_name: el
data_files:
- split: train
path: '*/*el*/train.parquet'
- split: test
path: '*/*el*/test.parquet'
- split: valid
path: '*/*el*/valid.parquet'
- config_name: en
data_files:
- split: train
path: '*/*en*/train.parquet'
- split: test
path: '*/*en*/test.parquet'
- split: valid
path: '*/*en*/valid.parquet'
- config_name: eo
data_files:
- split: train
path: '*/*eo*/train.parquet'
- split: test
path: '*/*eo*/test.parquet'
- split: valid
path: '*/*eo*/valid.parquet'
- config_name: es
data_files:
- split: train
path: '*/*es*/train.parquet'
- split: test
path: '*/*es*/test.parquet'
- split: valid
path: '*/*es*/valid.parquet'
- config_name: et
data_files:
- split: train
path: '*/*et*/train.parquet'
- split: test
path: '*/*et*/test.parquet'
- split: valid
path: '*/*et*/valid.parquet'
- config_name: eu
data_files:
- split: train
path: '*/*eu*/train.parquet'
- split: test
path: '*/*eu*/test.parquet'
- split: valid
path: '*/*eu*/valid.parquet'
- config_name: fa
data_files:
- split: train
path: '*/*fa*/train.parquet'
- split: test
path: '*/*fa*/test.parquet'
- split: valid
path: '*/*fa*/valid.parquet'
- config_name: fi
data_files:
- split: train
path: '*/*fi*/train.parquet'
- split: test
path: '*/*fi*/test.parquet'
- split: valid
path: '*/*fi*/valid.parquet'
- config_name: fr
data_files:
- split: train
path: '*/*fr*/train.parquet'
- split: test
path: '*/*fr*/test.parquet'
- split: valid
path: '*/*fr*/valid.parquet'
- config_name: ga
data_files:
- split: train
path: '*/*ga*/train.parquet'
- split: test
path: '*/*ga*/test.parquet'
- split: valid
path: '*/*ga*/valid.parquet'
- config_name: gl
data_files:
- split: train
path: '*/*gl*/train.parquet'
- split: test
path: '*/*gl*/test.parquet'
- split: valid
path: '*/*gl*/valid.parquet'
- config_name: he
data_files:
- split: train
path: '*/*he*/train.parquet'
- split: test
path: '*/*he*/test.parquet'
- split: valid
path: '*/*he*/valid.parquet'
- config_name: hi
data_files:
- split: train
path: '*/*hi*/train.parquet'
- split: test
path: '*/*hi*/test.parquet'
- split: valid
path: '*/*hi*/valid.parquet'
- config_name: hr
data_files:
- split: train
path: '*/*hr*/train.parquet'
- split: test
path: '*/*hr*/test.parquet'
- split: valid
path: '*/*hr*/valid.parquet'
- config_name: hu
data_files:
- split: train
path: '*/*hu*/train.parquet'
- split: test
path: '*/*hu*/test.parquet'
- split: valid
path: '*/*hu*/valid.parquet'
- config_name: hy
data_files:
- split: train
path: '*/*hy*/train.parquet'
- split: test
path: '*/*hy*/test.parquet'
- split: valid
path: '*/*hy*/valid.parquet'
- config_name: id
data_files:
- split: train
path: '*/*id*/train.parquet'
- split: test
path: '*/*id*/test.parquet'
- split: valid
path: '*/*id*/valid.parquet'
- config_name: is
data_files:
- split: train
path: '*/*is*/train.parquet'
- split: test
path: '*/*is*/test.parquet'
- split: valid
path: '*/*is*/valid.parquet'
- config_name: it
data_files:
- split: train
path: '*/*it*/train.parquet'
- split: test
path: '*/*it*/test.parquet'
- split: valid
path: '*/*it*/valid.parquet'
- config_name: ja
data_files:
- split: train
path: '*/*ja*/train.parquet'
- split: test
path: '*/*ja*/test.parquet'
- split: valid
path: '*/*ja*/valid.parquet'
- config_name: ka
data_files:
- split: train
path: '*/*ka*/train.parquet'
- split: test
path: '*/*ka*/test.parquet'
- split: valid
path: '*/*ka*/valid.parquet'
- config_name: kk
data_files:
- split: train
path: '*/*kk*/train.parquet'
- split: test
path: '*/*kk*/test.parquet'
- split: valid
path: '*/*kk*/valid.parquet'
- config_name: km
data_files:
- split: train
path: '*/*km*/train.parquet'
- split: test
path: '*/*km*/test.parquet'
- split: valid
path: '*/*km*/valid.parquet'
- config_name: kn
data_files:
- split: train
path: '*/*kn*/train.parquet'
- split: test
path: '*/*kn*/test.parquet'
- split: valid
path: '*/*kn*/valid.parquet'
- config_name: ko
data_files:
- split: train
path: '*/*ko*/train.parquet'
- split: test
path: '*/*ko*/test.parquet'
- split: valid
path: '*/*ko*/valid.parquet'
- config_name: ku
data_files:
- split: train
path: '*/*ku*/train.parquet'
- split: test
path: '*/*ku*/test.parquet'
- split: valid
path: '*/*ku*/valid.parquet'
- config_name: lo
data_files:
- split: train
path: '*/*lo*/train.parquet'
- split: test
path: '*/*lo*/test.parquet'
- split: valid
path: '*/*lo*/valid.parquet'
- config_name: lt
data_files:
- split: train
path: '*/*lt*/train.parquet'
- split: test
path: '*/*lt*/test.parquet'
- split: valid
path: '*/*lt*/valid.parquet'
- config_name: mg
data_files:
- split: train
path: '*/*mg*/train.parquet'
- split: test
path: '*/*mg*/test.parquet'
- split: valid
path: '*/*mg*/valid.parquet'
- config_name: mk
data_files:
- split: train
path: '*/*mk*/train.parquet'
- split: test
path: '*/*mk*/test.parquet'
- split: valid
path: '*/*mk*/valid.parquet'
- config_name: ml
data_files:
- split: train
path: '*/*ml*/train.parquet'
- split: test
path: '*/*ml*/test.parquet'
- split: valid
path: '*/*ml*/valid.parquet'
- config_name: mn
data_files:
- split: train
path: '*/*mn*/train.parquet'
- split: test
path: '*/*mn*/test.parquet'
- split: valid
path: '*/*mn*/valid.parquet'
- config_name: mr
data_files:
- split: train
path: '*/*mr*/train.parquet'
- split: test
path: '*/*mr*/test.parquet'
- split: valid
path: '*/*mr*/valid.parquet'
- config_name: ms
data_files:
- split: train
path: '*/*ms*/train.parquet'
- split: test
path: '*/*ms*/test.parquet'
- split: valid
path: '*/*ms*/valid.parquet'
- config_name: my
data_files:
- split: train
path: '*/*my*/train.parquet'
- split: test
path: '*/*my*/test.parquet'
- split: valid
path: '*/*my*/valid.parquet'
- config_name: ne
data_files:
- split: train
path: '*/*ne*/train.parquet'
- split: test
path: '*/*ne*/test.parquet'
- split: valid
path: '*/*ne*/valid.parquet'
- config_name: nl
data_files:
- split: train
path: '*/*nl*/train.parquet'
- split: test
path: '*/*nl*/test.parquet'
- split: valid
path: '*/*nl*/valid.parquet'
- config_name: pl
data_files:
- split: train
path: '*/*pl*/train.parquet'
- split: test
path: '*/*pl*/test.parquet'
- split: valid
path: '*/*pl*/valid.parquet'
- config_name: pt
data_files:
- split: train
path: '*/*pt*/train.parquet'
- split: test
path: '*/*pt*/test.parquet'
- split: valid
path: '*/*pt*/valid.parquet'
- config_name: ro
data_files:
- split: train
path: '*/*ro*/train.parquet'
- split: test
path: '*/*ro*/test.parquet'
- split: valid
path: '*/*ro*/valid.parquet'
- config_name: ru
data_files:
- split: train
path: '*/*ru*/train.parquet'
- split: test
path: '*/*ru*/test.parquet'
- split: valid
path: '*/*ru*/valid.parquet'
- config_name: sk
data_files:
- split: train
path: '*/*sk*/train.parquet'
- split: test
path: '*/*sk*/test.parquet'
- split: valid
path: '*/*sk*/valid.parquet'
- config_name: sl
data_files:
- split: train
path: '*/*sl*/train.parquet'
- split: test
path: '*/*sl*/test.parquet'
- split: valid
path: '*/*sl*/valid.parquet'
- config_name: so
data_files:
- split: train
path: '*/*so*/train.parquet'
- split: test
path: '*/*so*/test.parquet'
- split: valid
path: '*/*so*/valid.parquet'
- config_name: sq
data_files:
- split: train
path: '*/*sq*/train.parquet'
- split: test
path: '*/*sq*/test.parquet'
- split: valid
path: '*/*sq*/valid.parquet'
- config_name: sr
data_files:
- split: train
path: '*/*sr*/train.parquet'
- split: test
path: '*/*sr*/test.parquet'
- split: valid
path: '*/*sr*/valid.parquet'
- config_name: sv
data_files:
- split: train
path: '*/*sv*/train.parquet'
- split: test
path: '*/*sv*/test.parquet'
- split: valid
path: '*/*sv*/valid.parquet'
- config_name: sw
data_files:
- split: train
path: '*/*sw*/train.parquet'
- split: test
path: '*/*sw*/test.parquet'
- split: valid
path: '*/*sw*/valid.parquet'
- config_name: ta
data_files:
- split: train
path: '*/*ta*/train.parquet'
- split: test
path: '*/*ta*/test.parquet'
- split: valid
path: '*/*ta*/valid.parquet'
- config_name: te
data_files:
- split: train
path: '*/*te*/train.parquet'
- split: test
path: '*/*te*/test.parquet'
- split: valid
path: '*/*te*/valid.parquet'
- config_name: th
data_files:
- split: train
path: '*/*th*/train.parquet'
- split: test
path: '*/*th*/test.parquet'
- split: valid
path: '*/*th*/valid.parquet'
- config_name: tl
data_files:
- split: train
path: '*/*tl*/train.parquet'
- split: test
path: '*/*tl*/test.parquet'
- split: valid
path: '*/*tl*/valid.parquet'
- config_name: tr
data_files:
- split: train
path: '*/*tr*/train.parquet'
- split: test
path: '*/*tr*/test.parquet'
- split: valid
path: '*/*tr*/valid.parquet'
- config_name: ug
data_files:
- split: train
path: '*/*ug*/train.parquet'
- split: test
path: '*/*ug*/test.parquet'
- split: valid
path: '*/*ug*/valid.parquet'
- config_name: uk
data_files:
- split: train
path: '*/*uk*/train.parquet'
- split: test
path: '*/*uk*/test.parquet'
- split: valid
path: '*/*uk*/valid.parquet'
- config_name: ur
data_files:
- split: train
path: '*/*ur*/train.parquet'
- split: test
path: '*/*ur*/test.parquet'
- split: valid
path: '*/*ur*/valid.parquet'
- config_name: uz
data_files:
- split: train
path: '*/*uz*/train.parquet'
- split: test
path: '*/*uz*/test.parquet'
- split: valid
path: '*/*uz*/valid.parquet'
- config_name: vi
data_files:
- split: train
path: '*/*vi*/train.parquet'
- split: test
path: '*/*vi*/test.parquet'
- split: valid
path: '*/*vi*/valid.parquet'
- config_name: ky
data_files:
- split: train
path: '*/*ky*/train.parquet'
- split: test
path: '*/*ky*/test.parquet'
- split: valid
path: '*/*ky*/valid.parquet'
- config_name: si
data_files:
- split: train
path: '*/*si*/train.parquet'
- split: test
path: '*/*si*/test.parquet'
- split: valid
path: '*/*si*/valid.parquet'
- config_name: as
data_files:
- split: train
path: '*/*as*/train.parquet'
- split: test
path: '*/*as*/test.parquet'
- split: valid
path: '*/*as*/valid.parquet'
- config_name: ha
data_files:
- split: train
path: '*/*ha*/train.parquet'
- split: test
path: '*/*ha*/test.parquet'
- split: valid
path: '*/*ha*/valid.parquet'
- config_name: la
data_files:
- split: train
path: '*/*la*/train.parquet'
- split: test
path: '*/*la*/test.parquet'
- split: valid
path: '*/*la*/valid.parquet'
- config_name: pa
data_files:
- split: train
path: '*/*pa*/train.parquet'
- split: test
path: '*/*pa*/test.parquet'
- split: valid
path: '*/*pa*/valid.parquet'
- config_name: ps
data_files:
- split: train
path: '*/*ps*/train.parquet'
- split: test
path: '*/*ps*/test.parquet'
- split: valid
path: '*/*ps*/valid.parquet'
---

原始信息汇总

数据集概述

该数据集包含多个语言配置，每个配置包含训练、验证和测试数据文件。以下是各语言配置及其对应的数据文件路径：

默认配置

• 训练数据: */*/train.parquet
• 验证数据: */*/valid.parquet
• 测试数据: */*/test.parquet

语言配置

• af:
  • 训练数据: */*af*/train.parquet
  • 验证数据: */*af*/valid.parquet
  • 测试数据: */*af*/test.parquet
• am:
  • 训练数据: */*am*/train.parquet
  • 验证数据: */*am*/valid.parquet
  • 测试数据: */*am*/test.parquet
• ar:
  • 训练数据: */*ar*/train.parquet
  • 验证数据: */*ar*/valid.parquet
  • 测试数据: */*ar*/test.parquet
• az:
  • 训练数据: */*az*/train.parquet
  • 验证数据: */*az*/valid.parquet
  • 测试数据: */*az*/test.parquet
• be:
  • 训练数据: */*be*/train.parquet
  • 验证数据: */*be*/valid.parquet
  • 测试数据: */*be*/test.parquet
• bg:
  • 训练数据: */*bg*/train.parquet
  • 验证数据: */*bg*/valid.parquet
  • 测试数据: */*bg*/test.parquet
• bn:
  • 训练数据: */*bn*/train.parquet
  • 验证数据: */*bn*/valid.parquet
  • 测试数据: */*bn*/test.parquet
• bs:
  • 训练数据: */*bs*/train.parquet
  • 验证数据: */*bs*/valid.parquet
  • 测试数据: */*bs*/test.parquet
• ca:
  • 训练数据: */*ca*/train.parquet
  • 验证数据: */*ca*/valid.parquet
  • 测试数据: */*ca*/test.parquet
• cs:
  • 训练数据: */*cs*/train.parquet
  • 验证数据: */*cs*/valid.parquet
  • 测试数据: */*cs*/test.parquet
• da:
  • 训练数据: */*da*/train.parquet
  • 验证数据: */*da*/valid.parquet
  • 测试数据: */*da*/test.parquet
• de:
  • 训练数据: */*de*/train.parquet
  • 验证数据: */*de*/valid.parquet
  • 测试数据: */*de*/test.parquet
• el:
  • 训练数据: */*el*/train.parquet
  • 验证数据: */*el*/valid.parquet
  • 测试数据: */*el*/test.parquet
• en:
  • 训练数据: */*en*/train.parquet
  • 验证数据: */*en*/valid.parquet
  • 测试数据: */*en*/test.parquet
• eo:
  • 训练数据: */*eo*/train.parquet
  • 验证数据: */*eo*/valid.parquet
  • 测试数据: */*eo*/test.parquet
• es:
  • 训练数据: */*es*/train.parquet
  • 验证数据: */*es*/valid.parquet
  • 测试数据: */*es*/test.parquet
• et:
  • 训练数据: */*et*/train.parquet
  • 验证数据: */*et*/valid.parquet
  • 测试数据: */*et*/test.parquet
• eu:
  • 训练数据: */*eu*/train.parquet
  • 验证数据: */*eu*/valid.parquet
  • 测试数据: */*eu*/test.parquet
• fa:
  • 训练数据: */*fa*/train.parquet
  • 验证数据: */*fa*/valid.parquet
  • 测试数据: */*fa*/test.parquet
• fi:
  • 训练数据: */*fi*/train.parquet
  • 验证数据: */*fi*/valid.parquet
  • 测试数据: */*fi*/test.parquet
• fr:
  • 训练数据: */*fr*/train.parquet
  • 验证数据: */*fr*/valid.parquet
  • 测试数据: */*fr*/test.parquet
• ga:
  • 训练数据: */*ga*/train.parquet
  • 验证数据: */*ga*/valid.parquet
  • 测试数据: */*ga*/test.parquet
• gl:
  • 训练数据: */*gl*/train.parquet
  • 验证数据: */*gl*/valid.parquet
  • 测试数据: */*gl*/test.parquet
• he:
  • 训练数据: */*he*/train.parquet
  • 验证数据: */*he*/valid.parquet
  • 测试数据: */*he*/test.parquet
• hi:
  • 训练数据: */*hi*/train.parquet
  • 验证数据: */*hi*/valid.parquet
  • 测试数据: */*hi*/test.parquet
• hr:
  • 训练数据: */*hr*/train.parquet
  • 验证数据: */*hr*/valid.parquet
  • 测试数据: */*hr*/test.parquet
• hu:
  • 训练数据: */*hu*/train.parquet
  • 验证数据: */*hu*/valid.parquet
  • 测试数据: */*hu*/test.parquet
• hy:
  • 训练数据: */*hy*/train.parquet
  • 验证数据: */*hy*/valid.parquet
  • 测试数据: */*hy*/test.parquet
• id:
  • 训练数据: */*id*/train.parquet
  • 验证数据: */*id*/valid.parquet
  • 测试数据: */*id*/test.parquet
• is:
  • 训练数据: */*is*/train.parquet
  • 验证数据: */*is*/valid.parquet
  • 测试数据: */*is*/test.parquet
• it:
  • 训练数据: */*it*/train.parquet
  • 验证数据: */*it*/valid.parquet
  • 测试数据: */*it*/test.parquet
• ja:
  • 训练数据: */*ja*/train.parquet
  • 验证数据: */*ja*/valid.parquet
  • 测试数据: */*ja*/test.parquet
• ka:
  • 训练数据: */*ka*/train.parquet
  • 验证数据: */*ka*/valid.parquet
  • 测试数据: */*ka*/test.parquet
• kk:
  • 训练数据: */*kk*/train.parquet
  • 验证数据: */*kk*/valid.parquet
  • 测试数据: */*kk*/test.parquet
• km:
  • 训练数据: */*km*/train.parquet
  • 验证数据: */*km*/valid.parquet
  • 测试数据: */*km*/test.parquet
• kn:
  • 训练数据: */*kn*/train.parquet
  • 验证数据: */*kn*/valid.parquet
  • 测试数据: */*kn*/test.parquet
• ko:
  • 训练数据: */*ko*/train.parquet
  • 验证数据: */*ko*/valid.parquet
  • 测试数据: */*ko*/test.parquet
• ku:
  • 训练数据: */*ku*/train.parquet
  • 验证数据: */*ku*/valid.parquet
  • 测试数据: */*ku*/test.parquet
• lo:
  • 训练数据: */*lo*/train.parquet
  • 验证数据: */*lo*/valid.parquet
  • 测试数据: */*lo*/test.parquet
• lt:
  • 训练数据: */*lt*/train.parquet
  • 验证数据: */*lt*/valid.parquet
  • 测试数据: */*lt*/test.parquet
• mg:
  • 训练数据: */*mg*/train.parquet
  • 验证数据: */*mg*/valid.parquet
  • 测试数据: */*mg*/test.parquet
• mk:
  • 训练数据: */*mk*/train.parquet
  • 验证数据: */*mk*/valid.parquet
  • 测试数据: */*mk*/test.parquet
• ml:
  • 训练数据: */*ml*/train.parquet
  • 验证数据: */*ml*/valid.parquet
  • 测试数据: */*ml*/test.parquet
• mn:
  • 训练数据: */*mn*/train.parquet
  • 验证数据: */*mn*/valid.parquet
  • 测试数据: */*mn*/test.parquet
• mr:
  • 训练数据: */*mr*/train.parquet
  • 验证数据: */*mr*/valid.parquet
  • 测试数据: */*mr*/test.parquet
• ms:
  • 训练数据: */*ms*/train.parquet
  • 验证数据: */*ms*/valid.parquet
  • 测试数据: */*ms*/test.parquet
• my:
  • 训练数据: */*my*/train.parquet
  • 验证数据: */*my*/valid.parquet
  • 测试数据: */*my*/test.parquet
• ne:
  • 训练数据: */*ne*/train.parquet
  • 验证数据: */*ne*/valid.parquet
  • 测试数据: */*ne*/test.parquet
• nl:
  • 训练数据: */*nl*/train.parquet
  • 验证数据: */*nl*/valid.parquet
  • 测试数据: */*nl*/test.parquet
• pl:
  • 训练数据: */*pl*/train.parquet
  • 验证数据: */*pl*/valid.parquet
  • 测试数据: */*pl*/test.parquet
• pt:
  • 训练数据: */*pt*/train.parquet
  • 验证数据: */*pt*/valid.parquet
  • 测试数据: */*pt*/test.parquet
• ro:
  • 训练数据: */*ro*/train.parquet
  • 验证数据: */*ro*/valid.parquet
  • 测试数据: */*ro*/test.parquet
• ru:
  • 训练数据: */*ru*/train.parquet
  • 验证数据: */*ru*/valid.parquet
  • 测试数据: */*ru*/test.parquet
• sk:
  • 训练数据: */*sk*/train.parquet
  • 验证数据: */*sk*/valid.parquet
  • 测试数据: */*sk*/test.parquet
• sl:
  • 训练数据: */*sl*/train.parquet
  • 验证数据: */*sl*/valid.parquet
  • 测试数据: */*sl*/test.parquet
• so:
  • 训练数据: */*so*/train.parquet
  • 验证数据: */*so*/valid.parquet
  • 测试数据: */*so*/test.parquet
• sq:
  • 训练数据: */*sq*/train.parquet
  • 验证数据: */*sq*/valid.parquet
  • 测试数据: */*sq*/test.parquet
• sr:
  • 训练数据: */*sr*/train.parquet
  • 验证数据: */*sr*/valid.parquet
  • 测试数据: */*sr*/test.parquet
• sv:
  • 训练数据: */*sv*/train.parquet
  • 验证数据: */*sv*/valid.parquet
  • 测试数据: */*sv*/test.parquet
• sw:
  • 训练数据: */*sw*/train.parquet
  • 验证数据: */*sw*/valid.parquet
  • 测试数据: */*sw*/test.parquet
• ta:
  • 训练数据: */*ta*/train.parquet
  • 验证数据: */*ta*/valid.parquet
  • 测试数据: */*ta*/test.parquet
• te:
  • 训练数据: */*te*/train.parquet
  • 验证数据: */*te*/valid.parquet
  • 测试数据: */*te*/test.parquet
• th:
  • 训练数据: */*th*/train.parquet
  • 验证数据: */*th*/valid.parquet
  • 测试数据: */*th*/test.parquet
• tl:
  • 训练数据: */*tl*/train.parquet
  • 验证数据: */*tl*/valid.parquet
  • 测试数据: */*tl*/test.parquet
• tr:
  • 训练数据: */*tr*/train.parquet
  • 验证数据: */*tr*/valid.parquet
  • 测试数据: */*tr*/test.parquet
• ug:
  • 训练数据: */*ug*/train.parquet
  • 验证数据: */*ug*/valid.parquet
  • 测试数据: */*ug*/test.parquet
• uk:
  • 训练数据: */*uk*/train.parquet
  • 验证数据: */*uk*/valid.parquet
  • 测试数据: */*uk*/test.parquet
• ur:
  • 训练数据: */*ur*/train.parquet
  • 验证数据: */*ur*/valid.parquet
  • 测试数据: */*ur*/test.parquet
• uz:
  • 训练数据: */*uz*/train.parquet
  • 验证数据: */*uz*/valid.parquet
  • 测试数据: */*uz*/test.parquet
• vi:
  • 训练数据: */*vi*/train.parquet
  • 验证数据: */*vi*/valid.parquet
  • 测试数据: */*vi*/test.parquet
• ky: