loicmagne/open-subtitles-256s-bitext-mining
收藏数据集概述
数据集配置列表
-
config_name: af-ar
data_files: data/af-ar.jsonl -
config_name: af-bg
data_files: data/af-bg.jsonl -
config_name: af-bn
data_files: data/af-bn.jsonl -
config_name: af-bs
data_files: data/af-bs.jsonl -
config_name: af-cs
data_files: data/af-cs.jsonl -
config_name: af-da
data_files: data/af-da.jsonl -
config_name: af-de
data_files: data/af-de.jsonl -
config_name: af-el
data_files: data/af-el.jsonl -
config_name: af-en
data_files: data/af-en.jsonl -
config_name: af-eo
data_files: data/af-eo.jsonl -
config_name: af-es
data_files: data/af-es.jsonl -
config_name: af-et
data_files: data/af-et.jsonl -
config_name: af-fa
data_files: data/af-fa.jsonl -
config_name: af-fi
data_files: data/af-fi.jsonl -
config_name: af-fr
data_files: data/af-fr.jsonl -
config_name: af-he
data_files: data/af-he.jsonl -
config_name: af-hi
data_files: data/af-hi.jsonl -
config_name: af-hr
data_files: data/af-hr.jsonl -
config_name: af-hu
data_files: data/af-hu.jsonl -
config_name: af-id
data_files: data/af-id.jsonl -
config_name: af-it
data_files: data/af-it.jsonl -
config_name: af-ja
data_files: data/af-ja.jsonl -
config_name: af-lt
data_files: data/af-lt.jsonl -
config_name: af-lv
data_files: data/af-lv.jsonl -
config_name: af-mk
data_files: data/af-mk.jsonl -
config_name: af-ml
data_files: data/af-ml.jsonl -
config_name: af-ms
data_files: data/af-ms.jsonl -
config_name: af-nl
data_files: data/af-nl.jsonl -
config_name: af-no
data_files: data/af-no.jsonl -
config_name: af-pl
data_files: data/af-pl.jsonl -
config_name: af-pt
data_files: data/af-pt.jsonl -
config_name: af-ro
data_files: data/af-ro.jsonl -
config_name: af-ru
data_files: data/af-ru.jsonl -
config_name: af-si
data_files: data/af-si.jsonl -
config_name: af-sk
data_files: data/af-sk.jsonl -
config_name: af-sl
data_files: data/af-sl.jsonl -
config_name: af-sq
data_files: data/af-sq.jsonl -
config_name: af-sr
data_files: data/af-sr.jsonl -
config_name: af-sv
data_files: data/af-sv.jsonl -
config_name: af-ta
data_files: data/af-ta.jsonl -
config_name: af-th
data_files: data/af-th.jsonl -
config_name: af-tr
data_files: data/af-tr.jsonl -
config_name: af-uk
data_files: data/af-uk.jsonl -
config_name: af-vi
data_files: data/af-vi.jsonl -
config_name: af-pt_br
data_files: data/af-pt_br.jsonl -
config_name: af-ze_en
data_files: data/af-ze_en.jsonl -
config_name: af-zh_cn
data_files: data/af-zh_cn.jsonl -
config_name: af-zh_tw
data_files: data/af-zh_tw.jsonl -
config_name: ar-bg
data_files: data/ar-bg.jsonl -
config_name: ar-bn
data_files: data/ar-bn.jsonl -
config_name: ar-br
data_files: data/ar-br.jsonl -
config_name: ar-bs
data_files: data/ar-bs.jsonl -
config_name: ar-ca
data_files: data/ar-ca.jsonl -
config_name: ar-cs
data_files: data/ar-cs.jsonl -
config_name: ar-da
data_files: data/ar-da.jsonl -
config_name: ar-de
data_files: data/ar-de.jsonl -
config_name: ar-el
data_files: data/ar-el.jsonl -
config_name: ar-en
data_files: data/ar-en.jsonl -
config_name: ar-eo
data_files: data/ar-eo.jsonl -
config_name: ar-es
data_files: data/ar-es.jsonl -
config_name: ar-et
data_files: data/ar-et.jsonl -
config_name: ar-eu
data_files: data/ar-eu.jsonl -
config_name: ar-fa
data_files: data/ar-fa.jsonl -
config_name: ar-fi
data_files: data/ar-fi.jsonl -
config_name: ar-fr
data_files: data/ar-fr.jsonl -
config_name: ar-gl
data_files: data/ar-gl.jsonl -
config_name: ar-he
data_files: data/ar-he.jsonl -
config_name: ar-hi
data_files: data/ar-hi.jsonl -
config_name: ar-hr
data_files: data/ar-hr.jsonl -
config_name: ar-hu
data_files: data/ar-hu.jsonl -
config_name: ar-hy
data_files: data/ar-hy.jsonl -
config_name: ar-id
data_files: data/ar-id.jsonl -
config_name: ar-is
data_files: data/ar-is.jsonl -
config_name: ar-it
data_files: data/ar-it.jsonl -
config_name: ar-ja
data_files: data/ar-ja.jsonl -
config_name: ar-ka
data_files: data/ar-ka.jsonl -
config_name: ar-kk
data_files: data/ar-kk.jsonl -
config_name: ar-ko
data_files: data/ar-ko.jsonl -
config_name: ar-lt
data_files: data/ar-lt.jsonl -
config_name: ar-lv
data_files: data/ar-lv.jsonl -
config_name: ar-mk
data_files: data/ar-mk.jsonl -
config_name: ar-ml
data_files: data/ar-ml.jsonl -
config_name: ar-ms
data_files: data/ar-ms.jsonl -
config_name: ar-nl
data_files: data/ar-nl.jsonl -
config_name: ar-no
data_files: data/ar-no.jsonl -
config_name: ar-pl
data_files: data/ar-pl.jsonl -
config_name: ar-pt
data_files: data/ar-pt.jsonl -
config_name: ar-ro
data_files: data/ar-ro.jsonl -
config_name: ar-ru
data_files: data/ar-ru.jsonl -
config_name: ar-si
data_files: data/ar-si.jsonl -
config_name: ar-sk
data_files: data/ar-sk.jsonl -
config_name: ar-sl
data_files: data/ar-sl.jsonl -
config_name: ar-sq
data_files: data/ar-sq.jsonl -
config_name: ar-sr
data_files: data/ar-sr.jsonl -
config_name: ar-sv
data_files: data/ar-sv.jsonl -
config_name: ar-ta
data_files: data/ar-ta.jsonl -
config_name: ar-te
data_files: data/ar-te.jsonl -
config_name: ar-th
data_files: data/ar-th.jsonl -
config_name: ar-tl
data_files: data/ar-tl.jsonl -
config_name: ar-tr
data_files: data/ar-tr.jsonl -
config_name: ar-uk
data_files: data/ar-uk.jsonl -
config_name: ar-ur
data_files: data/ar-ur.jsonl -
config_name: ar-vi
data_files: data/ar-vi.jsonl -
config_name: ar-pt_br
data_files: data/ar-pt_br.jsonl -
config_name: ar-ze_en
data_files: data/ar-ze_en.jsonl -
config_name: ar-ze_zh
data_files: data/ar-ze_zh.jsonl -
config_name: ar-zh_cn
data_files: data/ar-zh_cn.jsonl -
config_name: ar-zh_tw
data_files: data/ar-zh_tw.jsonl -
config_name: bg-bn
data_files: data/bg-bn.jsonl -
config_name: bg-br
data_files: data/bg-br.jsonl -
config_name: bg-bs
data_files: data/bg-bs.jsonl -
config_name: bg-ca
data_files: data/bg-ca.jsonl -
config_name: bg-cs
data_files: data/bg-cs.jsonl -
config_name: bg-da
data_files: data/bg-da.jsonl -
config_name: bg-de
data_files: data/bg-de.jsonl -
config_name: bg-el
data_files: data/bg-el.jsonl -
config_name: bg-en
data_files: data/bg-en.jsonl -
config_name: bg-eo
data_files: data/bg-eo.jsonl -
config_name: bg-es
data_files: data/bg-es.jsonl -
config_name: bg-et
data_files: data/bg-et.jsonl -
config_name: bg-eu
data_files: data/bg-eu.jsonl -
config_name: bg-fa
data_files: data/bg-fa.jsonl -
config_name: bg-fi
data_files: data/bg-fi.jsonl -
config_name: bg-fr
data_files: data/bg-fr.jsonl -
config_name: bg-gl
data_files: data/bg-gl.jsonl -
config_name: bg-he
data_files: data/bg-he.jsonl -
config_name: bg-hi
data_files: data/bg-hi.jsonl -
config_name: bg-hr
data_files: data/bg-hr.jsonl -
config_name: bg-hu
data_files: data/bg-hu.jsonl -
config_name: bg-hy
data_files: data/bg-hy.jsonl -
config_name: bg-id
data_files: data/bg-id.jsonl -
config_name: bg-is
data_files: data/bg-is.jsonl -
config_name: bg-it
data_files: data/bg-it.jsonl -
config_name: bg-ja
data_files: data/bg-ja.jsonl -
config_name: bg-ka
data_files: data/bg-ka.jsonl -
config_name: bg-kk
data_files: data/bg-kk.jsonl -
config_name: bg-ko
data_files: data/bg-ko.jsonl -
config_name: bg-lt
data_files: data/bg-lt.jsonl -
config_name: bg-lv
data_files: data/bg-lv.jsonl -
config_name: bg-mk
data_files: data/bg-mk.jsonl -
config_name: bg-ml
data_files: data/bg-ml.jsonl -
config_name: bg-ms
data_files: data/bg-ms.jsonl -
config_name: bg-nl
data_files: data/bg-nl.jsonl -
config_name: bg-no
data_files: data/bg-no.jsonl -
config_name: bg-pl
data_files: data/bg-pl.jsonl -
config_name: bg-pt
data_files: data/bg-pt.jsonl -
config_name: bg-ro
data_files: data/bg-ro.jsonl -
config_name: bg-ru
data_files: data/bg-ru.jsonl -
config_name: bg-si
data_files: data/bg-si.jsonl -
config_name: bg-sk
data_files: data/bg



