wecover/OPUS_Tatoeba

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

原始信息汇总

数据集配置

该数据集包含多个配置，每个配置对应不同的语言和数据文件路径。以下是各配置的详细信息：

默认配置

• 配置名称: default
• 数据文件:
  • 训练集: */*/train.parquet
  • 验证集: */*/valid.parquet

语言配置

• 配置名称: af

• 数据文件:

  • 训练集: */*af*/train.parquet
  • 验证集: */*af*/valid.parquet

• 配置名称: ar

• 数据文件:

  • 训练集: */*ar*/train.parquet
  • 验证集: */*ar*/valid.parquet

• 配置名称: ca

• 数据文件:

  • 训练集: */*ca*/train.parquet
  • 验证集: */*ca*/valid.parquet

• 配置名称: cs

• 数据文件:

  • 训练集: */*cs*/train.parquet
  • 验证集: */*cs*/valid.parquet

• 配置名称: de

• 数据文件:

  • 训练集: */*de*/train.parquet
  • 验证集: */*de*/valid.parquet

• 配置名称: en

• 数据文件:

  • 训练集: */*en*/train.parquet
  • 验证集: */*en*/valid.parquet

• 配置名称: eo

• 数据文件:

  • 训练集: */*eo*/train.parquet
  • 验证集: */*eo*/valid.parquet

• 配置名称: es

• 数据文件:

  • 训练集: */*es*/train.parquet
  • 验证集: */*es*/valid.parquet

• 配置名称: fi

• 数据文件:

  • 训练集: */*fi*/train.parquet
  • 验证集: */*fi*/valid.parquet

• 配置名称: fr

• 数据文件:

  • 训练集: */*fr*/train.parquet
  • 验证集: */*fr*/valid.parquet

• 配置名称: ga

• 数据文件:

  • 训练集: */*ga*/train.parquet
  • 验证集: */*ga*/valid.parquet

• 配置名称: it

• 数据文件:

  • 训练集: */*it*/train.parquet
  • 验证集: */*it*/valid.parquet

• 配置名称: ja

• 数据文件:

  • 训练集: */*ja*/train.parquet
  • 验证集: */*ja*/valid.parquet

• 配置名称: la

• 数据文件:

  • 训练集: */*la*/train.parquet
  • 验证集: */*la*/valid.parquet

• 配置名称: nl

• 数据文件:

  • 训练集: */*nl*/train.parquet
  • 验证集: */*nl*/valid.parquet

• 配置名称: pl

• 数据文件:

  • 训练集: */*pl*/train.parquet
  • 验证集: */*pl*/valid.parquet

• 配置名称: pt

• 数据文件:

  • 训练集: */*pt*/train.parquet
  • 验证集: */*pt*/valid.parquet

• 配置名称: ro

• 数据文件:

  • 训练集: */*ro*/train.parquet
  • 验证集: */*ro*/valid.parquet

• 配置名称: ru

• 数据文件:

  • 训练集: */*ru*/train.parquet
  • 验证集: */*ru*/valid.parquet

• 配置名称: sv

• 数据文件:

  • 训练集: */*sv*/train.parquet
  • 验证集: */*sv*/valid.parquet

• 配置名称: tr

• 数据文件:

  • 训练集: */*tr*/train.parquet
  • 验证集: */*tr*/valid.parquet

• 配置名称: uk

• 数据文件:

  • 训练集: */*uk*/train.parquet
  • 验证集: */*uk*/valid.parquet

• 配置名称: xh

• 数据文件:

  • 训练集: */*xh*/train.parquet
  • 验证集: */*xh*/valid.parquet

• 配置名称: yi

• 数据文件:

  • 训练集: */*yi*/train.parquet
  • 验证集: */*yi*/valid.parquet

• 配置名称: am

• 数据文件:

  • 训练集: */*am*/train.parquet
  • 验证集: */*am*/valid.parquet

• 配置名称: bg

• 数据文件:

  • 训练集: */*bg*/train.parquet
  • 验证集: */*bg*/valid.parquet

• 配置名称: da

• 数据文件:

  • 训练集: */*da*/train.parquet
  • 验证集: */*da*/valid.parquet

• 配置名称: el

• 数据文件:

  • 训练集: */*el*/train.parquet
  • 验证集: */*el*/valid.parquet

• 配置名称: he

• 数据文件:

  • 训练集: */*he*/train.parquet
  • 验证集: */*he*/valid.parquet

• 配置名称: hu

• 数据文件:

  • 训练集: */*hu*/train.parquet
  • 验证集: */*hu*/valid.parquet

• 配置名称: ko

• 数据文件:

  • 训练集: */*ko*/train.parquet
  • 验证集: */*ko*/valid.parquet

• 配置名称: ku

• 数据文件:

  • 训练集: */*ku*/train.parquet
  • 验证集: */*ku*/valid.parquet

• 配置名称: lt

• 数据文件:

  • 训练集: */*lt*/train.parquet
  • 验证集: */*lt*/valid.parquet

• 配置名称: mk

• 数据文件:

  • 训练集: */*mk*/train.parquet
  • 验证集: */*mk*/valid.parquet

• 配置名称: ug

• 数据文件:

  • 训练集: */*ug*/train.parquet
  • 验证集: */*ug*/valid.parquet

• 配置名称: ur

• 数据文件:

  • 训练集: */*ur*/train.parquet
  • 验证集: */*ur*/valid.parquet

• 配置名称: as

• 数据文件:

  • 训练集: */*as*/train.parquet
  • 验证集: */*as*/valid.parquet

• 配置名称: bn

• 数据文件:

  • 训练集: */*bn*/train.parquet
  • 验证集: */*bn*/valid.parquet

• 配置名称: hi

• 数据文件:

  • 训练集: */*hi*/train.parquet
  • 验证集: */*hi*/valid.parquet

• 配置名称: az

• 数据文件:

  • 训练集: */*az*/train.parquet
  • 验证集: */*az*/valid.parquet

• 配置名称: kk

• 数据文件:

  • 训练集: */*kk*/train.parquet
  • 验证集: */*kk*/valid.parquet

• 配置名称: be

• 数据文件:

  • 训练集: */*be*/train.parquet
  • 验证集: */*be*/valid.parquet

• 配置名称: et

• 数据文件:

  • 训练集: */*et*/train.parquet
  • 验证集: */*et*/valid.parquet

• 配置名称: sl

• 数据文件:

  • 训练集: */*sl*/train.parquet
  • 验证集: */*sl*/valid.parquet

• 配置名称: sr

• 数据文件:

  • 训练集: */*sr*/train.parquet
  • 验证集: */*sr*/valid.parquet

• 配置名称: vi

• 数据文件:

  • 训练集: */*vi*/train.parquet
  • 验证集: */*vi*/valid.parquet

• 配置名称: id

• 数据文件:

  • 训练集: */*id*/train.parquet
  • 验证集: */*id*/valid.parquet

• 配置名称: br

• 数据文件:

  • 训练集: */*br*/train.parquet
  • 验证集: */*br*/valid.parquet

• 配置名称: bs

• 数据文件:

  • 训练集: */*bs*/train.parquet
  • 验证集: */*bs*/valid.parquet

• 配置名称: hr

• 数据文件:

  • 训练集: */*hr*/train.parquet
  • 验证集: */*hr*/valid.parquet

• 配置名称: gl

• 数据文件:

  • 训练集: */*gl*/train.parquet
  • 验证集: */*gl*/valid.parquet

• 配置名称: fy

• 数据文件:

  • 训练集: */*fy*/train.parquet
  • 验证集: */*fy*/valid.parquet

• 配置名称: ka

• 数据文件:

  • 训练集: */*ka*/train.parquet
  • 验证集: */*ka*/valid.parquet

• 配置名称: tl

• 数据文件:

  • 训练集: */*tl*/train.parquet
  • 验证集: */*tl*/valid.parquet

• 配置名称: cy

• 数据文件:

  • 训练集: */*cy*/train.parquet
  • 验证集: */*cy*/valid.parquet

• 配置名称: is

• 数据文件:

  • 训练集: */*is*/train.parquet
  • 验证集: */*is*/valid.parquet

• 配置名称: eu

• 数据文件:

  • 训练集: */*eu*/train.parquet
  • 验证集: */*eu*/valid.parquet

• 配置名称: gd

• 数据文件:

  • 训练集: */*gd*/train.parquet
  • 验证集: */*gd*/valid.parquet

• 配置名称: ha

• 数据文件:

  • 训练集: */*ha*/train.parquet
  • 验证集: */*ha*/valid.parquet

• 配置名称: hy

• 数据文件:

  • 训练集: */*hy*/train.parquet
  • 验证集: */*hy*/valid.parquet

• 配置名称: km

• 数据文件:

  • 训练集: */*km*/train.parquet
  • 验证集: */*km*/valid.parquet

• 配置名称: ky

• 数据文件:

  • 训练集: */*ky*/train.parquet
  • 验证集: */*ky*/valid.parquet

• 配置名称: mn

• 数据文件:

  • 训练集: */*mn*/train.parquet
  • 验证集: */*mn*/valid.parquet

• 配置名称: mr

• 数据文件:

  • 训练集: */*mr*/train.parquet
  • 验证集: */*mr*/valid.parquet

• 配置名称: my

• 数据文件:

  • 训练集: */*my*/train.parquet
  • 验证集: */*my*/valid.parquet

• 配置名称: th

• 数据文件:

  • 训练集: */*th*/train.parquet
  • 验证集: */*th*/valid.parquet

• 配置名称: uz

• 数据文件:

  • 训练集: */*uz*/train.parquet
  • 验证集: */*uz*/valid.parquet

• 配置名称: jv

• 数据文件:

  • 训练集: */*jv*/train.parquet
  • 验证集: */*jv*/valid.parquet

• 配置名称: kn

• 数据文件:

  • 训练集: */*kn*/train.parquet
  • 验证集: */*kn*/valid.parquet

• 配置名称: lo

• 数据文件:

  • 训练集: */*lo*/train.parquet
  • 验证集: */*lo*/valid.parquet

• 配置名称: mg

• 数据文件:

  • 训练集: */*mg*/train.parquet
  • 验证集: */*mg*/valid.parquet

• 配置名称: ml

• 数据文件:

  • 训练集: */*ml*/train.parquet
  • 验证集: */*ml*/valid.parquet

• 配置名称: or

• 数据文件:

  • 训练集: */*or*/train.parquet
  • 验证集: */*or*/valid.parquet

• 配置名称: pa

• 数据文件:

  • 训练集: */*pa*/train.parquet
  • 验证集: */*pa*/valid.parquet

• 配置名称: ps

• 数据文件:

  • 训练集: */*ps*/train.parquet
  • 验证集: */*ps*/valid.parquet

• 配置名称: sa

• 数据文件:

  • 训练集: */*sa*/train.parquet
  • 验证集: */*sa*/valid.parquet

• 配置名称: sd

• 数据文件:

  • 训练集: */*sd*/train.parquet

• 配置名称: si

• 数据文件:

  • 训练集: */*si*/train.parquet
  • 验证集: */*si*/valid.parquet

• 配置名称: so

• 数据文件:

  • 训练集: */*so*/train.parquet
  • 验证集: */*so*/valid.parquet

• 配置名称: sq

• 数据文件:

  • 训练集: */*sq*/train.parquet
  • 验证集: */*sq*/valid.parquet

• 配置名称: su

• 数据文件:

  • 训练集: */*su*/train.parquet
  • 验证集: */*su*/valid.parquet

• 配置名称: ta

• 数据文件:

  • 训练集: */*ta*/train.parquet
  • 验证集: */*ta*/valid.parquet

• 配置名称: te

• 数据文件:

  • 训练集: */*te*/train.parquet
  • 验证集: */*te*/valid.parquet