Name: hgissbkh/flores
Creator: hgissbkh
Published: 2026-04-13 15:06:40
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/hgissbkh/flores

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: ace_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 207980 num_examples: 1012 download_size: 111687 dataset_size: 207980 - config_name: ace_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 152553 num_examples: 1012 download_size: 98497 dataset_size: 152553 - config_name: acm_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 214508 num_examples: 1012 download_size: 121154 dataset_size: 214508 - config_name: acq_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 217381 num_examples: 1012 download_size: 123467 dataset_size: 217381 - config_name: aeb_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 211619 num_examples: 1012 download_size: 119727 dataset_size: 211619 - config_name: afr_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149388 num_examples: 1012 download_size: 102615 dataset_size: 149388 - config_name: ajp_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 204949 num_examples: 1012 download_size: 115946 dataset_size: 204949 - config_name: aka_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 153996 num_examples: 1012 download_size: 99183 dataset_size: 153996 - config_name: als_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 166602 num_examples: 1012 download_size: 110424 dataset_size: 166602 - config_name: amh_Ethi features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 233546 num_examples: 1012 download_size: 129880 dataset_size: 233546 - config_name: apc_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 204006 num_examples: 1012 download_size: 115131 dataset_size: 204006 - config_name: arb_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 219359 num_examples: 1012 download_size: 124241 dataset_size: 219359 - config_name: arb_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 161920 num_examples: 1012 download_size: 115426 dataset_size: 161920 - config_name: ars_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 219638 num_examples: 1012 download_size: 124288 dataset_size: 219638 - config_name: ary_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 214238 num_examples: 1012 download_size: 121449 dataset_size: 214238 - config_name: arz_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 214596 num_examples: 1012 download_size: 120101 dataset_size: 214596 - config_name: asm_Beng features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 343158 num_examples: 1012 download_size: 154534 dataset_size: 343158 - config_name: ast_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149198 num_examples: 1012 download_size: 104655 dataset_size: 149198 - config_name: awa_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 338644 num_examples: 1012 download_size: 146017 dataset_size: 338644 - config_name: ayr_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149974 num_examples: 1012 download_size: 101718 dataset_size: 149974 - config_name: azb_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 223145 num_examples: 1012 download_size: 120408 dataset_size: 223145 - config_name: azj_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 174640 num_examples: 1012 download_size: 113865 dataset_size: 174640 - config_name: bak_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 253299 num_examples: 1012 download_size: 135955 dataset_size: 253299 - config_name: bam_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 145662 num_examples: 1012 download_size: 95635 dataset_size: 145662 - config_name: ban_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154050 num_examples: 1012 download_size: 98069 dataset_size: 154050 - config_name: bel_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 278991 num_examples: 1012 download_size: 153979 dataset_size: 278991 - config_name: bem_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 169237 num_examples: 1012 download_size: 109185 dataset_size: 169237 - config_name: ben_Beng features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 352778 num_examples: 1012 download_size: 152848 dataset_size: 352778 - config_name: bho_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 336650 num_examples: 1012 download_size: 143447 dataset_size: 336650 - config_name: bjn_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 231604 num_examples: 1012 download_size: 121668 dataset_size: 231604 - config_name: bjn_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 146507 num_examples: 1012 download_size: 96443 dataset_size: 146507 - config_name: bod_Tibt features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 447121 num_examples: 1012 download_size: 152768 dataset_size: 447121 - config_name: bos_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 143967 num_examples: 1012 download_size: 105634 dataset_size: 143967 - config_name: bug_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 151702 num_examples: 1012 download_size: 105668 dataset_size: 151702 - config_name: bul_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 258674 num_examples: 1012 download_size: 137735 dataset_size: 258674 - config_name: cat_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 156910 num_examples: 1012 download_size: 108504 dataset_size: 156910 - config_name: ceb_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 166835 num_examples: 1012 download_size: 106414 dataset_size: 166835 - config_name: ces_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150511 num_examples: 1012 download_size: 110583 dataset_size: 150511 - config_name: cjk_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147872 num_examples: 1012 download_size: 104804 dataset_size: 147872 - config_name: ckb_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 244463 num_examples: 1012 download_size: 127813 dataset_size: 244463 - config_name: crh_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155461 num_examples: 1012 download_size: 104625 dataset_size: 155461 - config_name: cym_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149893 num_examples: 1012 download_size: 103099 dataset_size: 149893 - config_name: dan_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 146084 num_examples: 1012 download_size: 101508 dataset_size: 146084 - config_name: deu_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 164454 num_examples: 1012 download_size: 112860 dataset_size: 164454 - config_name: dik_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 134459 num_examples: 1012 download_size: 90338 dataset_size: 134459 - config_name: dyu_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149666 num_examples: 1012 download_size: 107634 dataset_size: 149666 - config_name: dzo_Tibt features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 486216 num_examples: 1012 download_size: 165422 dataset_size: 486216 - config_name: ell_Grek features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 295317 num_examples: 1012 download_size: 159251 dataset_size: 295317 - config_name: eng_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 140192 num_examples: 1012 download_size: 97306 dataset_size: 140192 - config_name: epo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 141838 num_examples: 1012 download_size: 98915 dataset_size: 141838 - config_name: est_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 141575 num_examples: 1012 download_size: 102673 dataset_size: 141575 - config_name: eus_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 148365 num_examples: 1012 download_size: 101357 dataset_size: 148365 - config_name: ewe_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 148103 num_examples: 1012 download_size: 93904 dataset_size: 148103 - config_name: fao_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 152748 num_examples: 1012 download_size: 104449 dataset_size: 152748 - config_name: fij_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 163420 num_examples: 1012 download_size: 96807 dataset_size: 163420 - config_name: fin_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 153913 num_examples: 1012 download_size: 108126 dataset_size: 153913 - config_name: fon_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 175049 num_examples: 1012 download_size: 110629 dataset_size: 175049 - config_name: fra_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 172023 num_examples: 1012 download_size: 113719 dataset_size: 172023 - config_name: fur_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 157573 num_examples: 1012 download_size: 106247 dataset_size: 157573 - config_name: fuv_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 133239 num_examples: 1012 download_size: 95134 dataset_size: 133239 - config_name: gaz_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 166919 num_examples: 1012 download_size: 110514 dataset_size: 166919 - config_name: gla_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 177220 num_examples: 1012 download_size: 113171 dataset_size: 177220 - config_name: gle_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 170337 num_examples: 1012 download_size: 113604 dataset_size: 170337 - config_name: glg_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 157833 num_examples: 1012 download_size: 107922 dataset_size: 157833 - config_name: grn_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150930 num_examples: 1012 download_size: 98364 dataset_size: 150930 - config_name: guj_Gujr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 339164 num_examples: 1012 download_size: 149867 dataset_size: 339164 - config_name: hat_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 132766 num_examples: 1012 download_size: 91347 dataset_size: 132766 - config_name: hau_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149803 num_examples: 1012 download_size: 99739 dataset_size: 149803 - config_name: heb_Hebr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 191177 num_examples: 1012 download_size: 109484 dataset_size: 191177 - config_name: hin_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 345169 num_examples: 1012 download_size: 149058 dataset_size: 345169 - config_name: hne_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 334153 num_examples: 1012 download_size: 144298 dataset_size: 334153 - config_name: hrv_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 140262 num_examples: 1012 download_size: 103383 dataset_size: 140262 - config_name: hun_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 160678 num_examples: 1012 download_size: 113271 dataset_size: 160678 - config_name: hye_Armn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 277751 num_examples: 1012 download_size: 144972 dataset_size: 277751 - config_name: ibo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 169116 num_examples: 1012 download_size: 104538 dataset_size: 169116 - config_name: ilo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 168150 num_examples: 1012 download_size: 107327 dataset_size: 168150 - config_name: ind_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150543 num_examples: 1012 download_size: 97583 dataset_size: 150543 - config_name: isl_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 151545 num_examples: 1012 download_size: 106031 dataset_size: 151545 - config_name: ita_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 165355 num_examples: 1012 download_size: 112779 dataset_size: 165355 - config_name: jav_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 145283 num_examples: 1012 download_size: 96543 dataset_size: 145283 - config_name: jpn_Jpan features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 175205 num_examples: 1012 download_size: 111686 dataset_size: 175205 - config_name: kab_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147752 num_examples: 1012 download_size: 101923 dataset_size: 147752 - config_name: kac_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 177513 num_examples: 1012 download_size: 106754 dataset_size: 177513 - config_name: kam_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 141768 num_examples: 1012 download_size: 99832 dataset_size: 141768 - config_name: kan_Knda features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 383476 num_examples: 1012 download_size: 161039 dataset_size: 383476 - config_name: kas_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 236275 num_examples: 1012 download_size: 136077 dataset_size: 236275 - config_name: kas_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 325508 num_examples: 1012 download_size: 152833 dataset_size: 325508 - config_name: kat_Geor features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 397677 num_examples: 1012 download_size: 159292 dataset_size: 397677 - config_name: kaz_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 258077 num_examples: 1012 download_size: 135845 dataset_size: 258077 - config_name: kbp_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 188811 num_examples: 1012 download_size: 107792 dataset_size: 188811 - config_name: kea_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 142064 num_examples: 1012 download_size: 97996 dataset_size: 142064 - config_name: khk_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 260124 num_examples: 1012 download_size: 136577 dataset_size: 260124 - config_name: khm_Khmr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 443256 num_examples: 1012 download_size: 190772 dataset_size: 443256 - config_name: kik_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 178727 num_examples: 1012 download_size: 110169 dataset_size: 178727 - config_name: kin_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 157246 num_examples: 1012 download_size: 104256 dataset_size: 157246 - config_name: kir_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 258296 num_examples: 1012 download_size: 138344 dataset_size: 258296 - config_name: kmb_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154651 num_examples: 1012 download_size: 101277 dataset_size: 154651 - config_name: kmr_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 152827 num_examples: 1012 download_size: 105930 dataset_size: 152827 - config_name: knc_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 219471 num_examples: 1012 download_size: 116226 dataset_size: 219471 - config_name: knc_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154678 num_examples: 1012 download_size: 102638 dataset_size: 154678 - config_name: kon_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 158172 num_examples: 1012 download_size: 94925 dataset_size: 158172 - config_name: kor_Hang features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 165895 num_examples: 1012 download_size: 111113 dataset_size: 165895 - config_name: lao_Laoo features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 368805 num_examples: 1012 download_size: 159237 dataset_size: 368805 - config_name: lij_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 162512 num_examples: 1012 download_size: 111519 dataset_size: 162512 - config_name: lim_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150351 num_examples: 1012 download_size: 105668 dataset_size: 150351 - config_name: lin_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150483 num_examples: 1012 download_size: 90239 dataset_size: 150483 - config_name: lit_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147300 num_examples: 1012 download_size: 106388 dataset_size: 147300 - config_name: lmo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 161239 num_examples: 1012 download_size: 110883 dataset_size: 161239 - config_name: ltg_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 145984 num_examples: 1012 download_size: 104355 dataset_size: 145984 - config_name: ltz_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 159970 num_examples: 1012 download_size: 109645 dataset_size: 159970 - config_name: lua_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 151197 num_examples: 1012 download_size: 97945 dataset_size: 151197 - config_name: lug_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 144856 num_examples: 1012 download_size: 102358 dataset_size: 144856 - config_name: luo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 145997 num_examples: 1012 download_size: 98208 dataset_size: 145997 - config_name: lus_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154665 num_examples: 1012 download_size: 102234 dataset_size: 154665 - config_name: lvs_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154754 num_examples: 1012 download_size: 109245 dataset_size: 154754 - config_name: mag_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 334798 num_examples: 1012 download_size: 142446 dataset_size: 334798 - config_name: mai_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 343455 num_examples: 1012 download_size: 146001 dataset_size: 343455 - config_name: mal_Mlym features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 419849 num_examples: 1012 download_size: 173777 dataset_size: 419849 - config_name: mar_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 363607 num_examples: 1012 download_size: 156869 dataset_size: 363607 - config_name: min_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 239515 num_examples: 1012 download_size: 124828 dataset_size: 239515 - config_name: min_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 149390 num_examples: 1012 download_size: 98064 dataset_size: 149390 - config_name: mkd_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 259291 num_examples: 1012 download_size: 135747 dataset_size: 259291 - config_name: mlt_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 161893 num_examples: 1012 download_size: 110786 dataset_size: 161893 - config_name: mni_Beng features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 376026 num_examples: 1012 download_size: 151846 dataset_size: 376026 - config_name: mos_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 142960 num_examples: 1012 download_size: 99245 dataset_size: 142960 - config_name: mri_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 161897 num_examples: 1012 download_size: 97651 dataset_size: 161897 - config_name: mya_Mymr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 473624 num_examples: 1012 download_size: 174679 dataset_size: 473624 - config_name: nld_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155827 num_examples: 1012 download_size: 105812 dataset_size: 155827 - config_name: nno_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 144546 num_examples: 1012 download_size: 100435 dataset_size: 144546 - config_name: nob_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 143126 num_examples: 1012 download_size: 100207 dataset_size: 143126 - config_name: npi_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 347568 num_examples: 1012 download_size: 149363 dataset_size: 347568 - config_name: nso_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 163009 num_examples: 1012 download_size: 103809 dataset_size: 163009 - config_name: nus_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 182873 num_examples: 1012 download_size: 109008 dataset_size: 182873 - config_name: nya_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155618 num_examples: 1012 download_size: 101848 dataset_size: 155618 - config_name: oci_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 163466 num_examples: 1012 download_size: 109639 dataset_size: 163466 - config_name: ory_Orya features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 369555 num_examples: 1012 download_size: 157772 dataset_size: 369555 - config_name: pag_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 138039 num_examples: 1012 download_size: 94044 dataset_size: 138039 - config_name: pan_Guru features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 352268 num_examples: 1012 download_size: 154430 dataset_size: 352268 - config_name: pap_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150867 num_examples: 1012 download_size: 100708 dataset_size: 150867 - config_name: pbt_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 222951 num_examples: 1012 download_size: 125542 dataset_size: 222951 - config_name: pes_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 231597 num_examples: 1012 download_size: 126044 dataset_size: 231597 - config_name: plt_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 173799 num_examples: 1012 download_size: 104652 dataset_size: 173799 - config_name: pol_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 156347 num_examples: 1012 download_size: 114056 dataset_size: 156347 - config_name: por_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155544 num_examples: 1012 download_size: 106929 dataset_size: 155544 - config_name: prs_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 223113 num_examples: 1012 download_size: 121391 dataset_size: 223113 - config_name: quy_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 150262 num_examples: 1012 download_size: 98647 dataset_size: 150262 - config_name: ron_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 165021 num_examples: 1012 download_size: 112876 dataset_size: 165021 - config_name: run_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 156148 num_examples: 1012 download_size: 105824 dataset_size: 156148 - config_name: rus_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 268438 num_examples: 1012 download_size: 148508 dataset_size: 268438 - config_name: sag_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155479 num_examples: 1012 download_size: 91170 dataset_size: 155479 - config_name: san_Deva features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 354803 num_examples: 1012 download_size: 151660 dataset_size: 354803 - config_name: sat_Olck features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 377411 num_examples: 1012 download_size: 151866 dataset_size: 377411 - config_name: scn_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154118 num_examples: 1012 download_size: 106452 dataset_size: 154118 - config_name: shn_Mymr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 530574 num_examples: 1012 download_size: 204350 dataset_size: 530574 - config_name: sin_Sinh features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 354152 num_examples: 1012 download_size: 160979 dataset_size: 354152 - config_name: slk_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 151834 num_examples: 1012 download_size: 111822 dataset_size: 151834 - config_name: slv_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 142105 num_examples: 1012 download_size: 103946 dataset_size: 142105 - config_name: smo_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 168130 num_examples: 1012 download_size: 101011 dataset_size: 168130 - config_name: sna_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155718 num_examples: 1012 download_size: 103893 dataset_size: 155718 - config_name: snd_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 219977 num_examples: 1012 download_size: 121317 dataset_size: 219977 - config_name: som_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 160038 num_examples: 1012 download_size: 112751 dataset_size: 160038 - config_name: sot_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 167123 num_examples: 1012 download_size: 105757 dataset_size: 167123 - config_name: spa_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 167995 num_examples: 1012 download_size: 114106 dataset_size: 167995 - config_name: srd_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 165756 num_examples: 1012 download_size: 107886 dataset_size: 165756 - config_name: srp_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 246088 num_examples: 1012 download_size: 135454 dataset_size: 246088 - config_name: ssw_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 156852 num_examples: 1012 download_size: 105358 dataset_size: 156852 - config_name: sun_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 146334 num_examples: 1012 download_size: 99896 dataset_size: 146334 - config_name: swe_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 145486 num_examples: 1012 download_size: 101356 dataset_size: 145486 - config_name: swh_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 146404 num_examples: 1012 download_size: 97462 dataset_size: 146404 - config_name: szl_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 153627 num_examples: 1012 download_size: 114114 dataset_size: 153627 - config_name: tam_Taml features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 429737 num_examples: 1012 download_size: 168406 dataset_size: 429737 - config_name: taq_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 141147 num_examples: 1012 download_size: 100319 dataset_size: 141147 - config_name: taq_Tfng features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 311078 num_examples: 1012 download_size: 138759 dataset_size: 311078 - config_name: tat_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 252856 num_examples: 1012 download_size: 135619 dataset_size: 252856 - config_name: tel_Telu features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 361772 num_examples: 1012 download_size: 157121 dataset_size: 361772 - config_name: tgk_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 273615 num_examples: 1012 download_size: 143660 dataset_size: 273615 - config_name: tgl_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 174372 num_examples: 1012 download_size: 110339 dataset_size: 174372 - config_name: tha_Thai features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 372953 num_examples: 1012 download_size: 161106 dataset_size: 372953 - config_name: tir_Ethi features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 239895 num_examples: 1012 download_size: 136005 dataset_size: 239895 - config_name: tpi_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 177243 num_examples: 1012 download_size: 97866 dataset_size: 177243 - config_name: tsn_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 171343 num_examples: 1012 download_size: 110241 dataset_size: 171343 - config_name: tso_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 167260 num_examples: 1012 download_size: 104312 dataset_size: 167260 - config_name: tuk_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 162700 num_examples: 1012 download_size: 106999 dataset_size: 162700 - config_name: tum_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 182944 num_examples: 1012 download_size: 110578 dataset_size: 182944 - config_name: tur_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 155992 num_examples: 1012 download_size: 106157 dataset_size: 155992 - config_name: twi_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 146861 num_examples: 1012 download_size: 96575 dataset_size: 146861 - config_name: tzm_Tfng features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 311226 num_examples: 1012 download_size: 141292 dataset_size: 311226 - config_name: uig_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 269325 num_examples: 1012 download_size: 137461 dataset_size: 269325 - config_name: ukr_Cyrl features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 253982 num_examples: 1012 download_size: 143938 dataset_size: 253982 - config_name: umb_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147341 num_examples: 1012 download_size: 95453 dataset_size: 147341 - config_name: urd_Arab features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 239796 num_examples: 1012 download_size: 130850 dataset_size: 239796 - config_name: uzn_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 157570 num_examples: 1012 download_size: 105031 dataset_size: 157570 - config_name: vec_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147678 num_examples: 1012 download_size: 102832 dataset_size: 147678 - config_name: vie_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 191702 num_examples: 1012 download_size: 113276 dataset_size: 191702 - config_name: war_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 172927 num_examples: 1012 download_size: 107702 dataset_size: 172927 - config_name: wol_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 140300 num_examples: 1012 download_size: 102886 dataset_size: 140300 - config_name: xho_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 147340 num_examples: 1012 download_size: 104894 dataset_size: 147340 - config_name: ydd_Hebr features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 264743 num_examples: 1012 download_size: 134591 dataset_size: 264743 - config_name: yor_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 176949 num_examples: 1012 download_size: 115293 dataset_size: 176949 - config_name: yue_Hant features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 122529 num_examples: 1012 download_size: 95328 dataset_size: 122529 - config_name: zho_Hans features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 128899 num_examples: 1012 download_size: 100011 dataset_size: 128899 - config_name: zho_Hant features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 124295 num_examples: 1012 download_size: 98598 dataset_size: 124295 - config_name: zsm_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 154673 num_examples: 1012 download_size: 99210 dataset_size: 154673 - config_name: zul_Latn features: - name: id dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 156698 num_examples: 1012 download_size: 105787 dataset_size: 156698 configs: - config_name: ace_Arab data_files: - split: test path: ace_Arab/test-* - config_name: ace_Latn data_files: - split: test path: ace_Latn/test-* - config_name: acm_Arab data_files: - split: test path: acm_Arab/test-* - config_name: acq_Arab data_files: - split: test path: acq_Arab/test-* - config_name: aeb_Arab data_files: - split: test path: aeb_Arab/test-* - config_name: afr_Latn data_files: - split: test path: afr_Latn/test-* - config_name: ajp_Arab data_files: - split: test path: ajp_Arab/test-* - config_name: aka_Latn data_files: - split: test path: aka_Latn/test-* - config_name: als_Latn data_files: - split: test path: als_Latn/test-* - config_name: amh_Ethi data_files: - split: test path: amh_Ethi/test-* - config_name: apc_Arab data_files: - split: test path: apc_Arab/test-* - config_name: arb_Arab data_files: - split: test path: arb_Arab/test-* - config_name: arb_Latn data_files: - split: test path: arb_Latn/test-* - config_name: ars_Arab data_files: - split: test path: ars_Arab/test-* - config_name: ary_Arab data_files: - split: test path: ary_Arab/test-* - config_name: arz_Arab data_files: - split: test path: arz_Arab/test-* - config_name: asm_Beng data_files: - split: test path: asm_Beng/test-* - config_name: ast_Latn data_files: - split: test path: ast_Latn/test-* - config_name: awa_Deva data_files: - split: test path: awa_Deva/test-* - config_name: ayr_Latn data_files: - split: test path: ayr_Latn/test-* - config_name: azb_Arab data_files: - split: test path: azb_Arab/test-* - config_name: azj_Latn data_files: - split: test path: azj_Latn/test-* - config_name: bak_Cyrl data_files: - split: test path: bak_Cyrl/test-* - config_name: bam_Latn data_files: - split: test path: bam_Latn/test-* - config_name: ban_Latn data_files: - split: test path: ban_Latn/test-* - config_name: bel_Cyrl data_files: - split: test path: bel_Cyrl/test-* - config_name: bem_Latn data_files: - split: test path: bem_Latn/test-* - config_name: ben_Beng data_files: - split: test path: ben_Beng/test-* - config_name: bho_Deva data_files: - split: test path: bho_Deva/test-* - config_name: bjn_Arab data_files: - split: test path: bjn_Arab/test-* - config_name: bjn_Latn data_files: - split: test path: bjn_Latn/test-* - config_name: bod_Tibt data_files: - split: test path: bod_Tibt/test-* - config_name: bos_Latn data_files: - split: test path: bos_Latn/test-* - config_name: bug_Latn data_files: - split: test path: bug_Latn/test-* - config_name: bul_Cyrl data_files: - split: test path: bul_Cyrl/test-* - config_name: cat_Latn data_files: - split: test path: cat_Latn/test-* - config_name: ceb_Latn data_files: - split: test path: ceb_Latn/test-* - config_name: ces_Latn data_files: - split: test path: ces_Latn/test-* - config_name: cjk_Latn data_files: - split: test path: cjk_Latn/test-* - config_name: ckb_Arab data_files: - split: test path: ckb_Arab/test-* - config_name: crh_Latn data_files: - split: test path: crh_Latn/test-* - config_name: cym_Latn data_files: - split: test path: cym_Latn/test-* - config_name: dan_Latn data_files: - split: test path: dan_Latn/test-* - config_name: deu_Latn data_files: - split: test path: deu_Latn/test-* - config_name: dik_Latn data_files: - split: test path: dik_Latn/test-* - config_name: dyu_Latn data_files: - split: test path: dyu_Latn/test-* - config_name: dzo_Tibt data_files: - split: test path: dzo_Tibt/test-* - config_name: ell_Grek data_files: - split: test path: ell_Grek/test-* - config_name: eng_Latn data_files: - split: test path: eng_Latn/test-* - config_name: epo_Latn data_files: - split: test path: epo_Latn/test-* - config_name: est_Latn data_files: - split: test path: est_Latn/test-* - config_name: eus_Latn data_files: - split: test path: eus_Latn/test-* - config_name: ewe_Latn data_files: - split: test path: ewe_Latn/test-* - config_name: fao_Latn data_files: - split: test path: fao_Latn/test-* - config_name: fij_Latn data_files: - split: test path: fij_Latn/test-* - config_name: fin_Latn data_files: - split: test path: fin_Latn/test-* - config_name: fon_Latn data_files: - split: test path: fon_Latn/test-* - config_name: fra_Latn data_files: - split: test path: fra_Latn/test-* - config_name: fur_Latn data_files: - split: test path: fur_Latn/test-* - config_name: fuv_Latn data_files: - split: test path: fuv_Latn/test-* - config_name: gaz_Latn data_files: - split: test path: gaz_Latn/test-* - config_name: gla_Latn data_files: - split: test path: gla_Latn/test-* - config_name: gle_Latn data_files: - split: test path: gle_Latn/test-* - config_name: glg_Latn data_files: - split: test path: glg_Latn/test-* - config_name: grn_Latn data_files: - split: test path: grn_Latn/test-* - config_name: guj_Gujr data_files: - split: test path: guj_Gujr/test-* - config_name: hat_Latn data_files: - split: test path: hat_Latn/test-* - config_name: hau_Latn data_files: - split: test path: hau_Latn/test-* - config_name: heb_Hebr data_files: - split: test path: heb_Hebr/test-* - config_name: hin_Deva data_files: - split: test path: hin_Deva/test-* - config_name: hne_Deva data_files: - split: test path: hne_Deva/test-* - config_name: hrv_Latn data_files: - split: test path: hrv_Latn/test-* - config_name: hun_Latn data_files: - split: test path: hun_Latn/test-* - config_name: hye_Armn data_files: - split: test path: hye_Armn/test-* - config_name: ibo_Latn data_files: - split: test path: ibo_Latn/test-* - config_name: ilo_Latn data_files: - split: test path: ilo_Latn/test-* - config_name: ind_Latn data_files: - split: test path: ind_Latn/test-* - config_name: isl_Latn data_files: - split: test path: isl_Latn/test-* - config_name: ita_Latn data_files: - split: test path: ita_Latn/test-* - config_name: jav_Latn data_files: - split: test path: jav_Latn/test-* - config_name: jpn_Jpan data_files: - split: test path: jpn_Jpan/test-* - config_name: kab_Latn data_files: - split: test path: kab_Latn/test-* - config_name: kac_Latn data_files: - split: test path: kac_Latn/test-* - config_name: kam_Latn data_files: - split: test path: kam_Latn/test-* - config_name: kan_Knda data_files: - split: test path: kan_Knda/test-* - config_name: kas_Arab data_files: - split: test path: kas_Arab/test-* - config_name: kas_Deva data_files: - split: test path: kas_Deva/test-* - config_name: kat_Geor data_files: - split: test path: kat_Geor/test-* - config_name: kaz_Cyrl data_files: - split: test path: kaz_Cyrl/test-* - config_name: kbp_Latn data_files: - split: test path: kbp_Latn/test-* - config_name: kea_Latn data_files: - split: test path: kea_Latn/test-* - config_name: khk_Cyrl data_files: - split: test path: khk_Cyrl/test-* - config_name: khm_Khmr data_files: - split: test path: khm_Khmr/test-* - config_name: kik_Latn data_files: - split: test path: kik_Latn/test-* - config_name: kin_Latn data_files: - split: test path: kin_Latn/test-* - config_name: kir_Cyrl data_files: - split: test path: kir_Cyrl/test-* - config_name: kmb_Latn data_files: - split: test path: kmb_Latn/test-* - config_name: kmr_Latn data_files: - split: test path: kmr_Latn/test-* - config_name: knc_Arab data_files: - split: test path: knc_Arab/test-* - config_name: knc_Latn data_files: - split: test path: knc_Latn/test-* - config_name: kon_Latn data_files: - split: test path: kon_Latn/test-* - config_name: kor_Hang data_files: - split: test path: kor_Hang/test-* - config_name: lao_Laoo data_files: - split: test path: lao_Laoo/test-* - config_name: lij_Latn data_files: - split: test path: lij_Latn/test-* - config_name: lim_Latn data_files: - split: test path: lim_Latn/test-* - config_name: lin_Latn data_files: - split: test path: lin_Latn/test-* - config_name: lit_Latn data_files: - split: test path: lit_Latn/test-* - config_name: lmo_Latn data_files: - split: test path: lmo_Latn/test-* - config_name: ltg_Latn data_files: - split: test path: ltg_Latn/test-* - config_name: ltz_Latn data_files: - split: test path: ltz_Latn/test-* - config_name: lua_Latn data_files: - split: test path: lua_Latn/test-* - config_name: lug_Latn data_files: - split: test path: lug_Latn/test-* - config_name: luo_Latn data_files: - split: test path: luo_Latn/test-* - config_name: lus_Latn data_files: - split: test path: lus_Latn/test-* - config_name: lvs_Latn data_files: - split: test path: lvs_Latn/test-* - config_name: mag_Deva data_files: - split: test path: mag_Deva/test-* - config_name: mai_Deva data_files: - split: test path: mai_Deva/test-* - config_name: mal_Mlym data_files: - split: test path: mal_Mlym/test-* - config_name: mar_Deva data_files: - split: test path: mar_Deva/test-* - config_name: min_Arab data_files: - split: test path: min_Arab/test-* - config_name: min_Latn data_files: - split: test path: min_Latn/test-* - config_name: mkd_Cyrl data_files: - split: test path: mkd_Cyrl/test-* - config_name: mlt_Latn data_files: - split: test path: mlt_Latn/test-* - config_name: mni_Beng data_files: - split: test path: mni_Beng/test-* - config_name: mos_Latn data_files: - split: test path: mos_Latn/test-* - config_name: mri_Latn data_files: - split: test path: mri_Latn/test-* - config_name: mya_Mymr data_files: - split: test path: mya_Mymr/test-* - config_name: nld_Latn data_files: - split: test path: nld_Latn/test-* - config_name: nno_Latn data_files: - split: test path: nno_Latn/test-* - config_name: nob_Latn data_files: - split: test path: nob_Latn/test-* - config_name: npi_Deva data_files: - split: test path: npi_Deva/test-* - config_name: nso_Latn data_files: - split: test path: nso_Latn/test-* - config_name: nus_Latn data_files: - split: test path: nus_Latn/test-* - config_name: nya_Latn data_files: - split: test path: nya_Latn/test-* - config_name: oci_Latn data_files: - split: test path: oci_Latn/test-* - config_name: ory_Orya data_files: - split: test path: ory_Orya/test-* - config_name: pag_Latn data_files: - split: test path: pag_Latn/test-* - config_name: pan_Guru data_files: - split: test path: pan_Guru/test-* - config_name: pap_Latn data_files: - split: test path: pap_Latn/test-* - config_name: pbt_Arab data_files: - split: test path: pbt_Arab/test-* - config_name: pes_Arab data_files: - split: test path: pes_Arab/test-* - config_name: plt_Latn data_files: - split: test path: plt_Latn/test-* - config_name: pol_Latn data_files: - split: test path: pol_Latn/test-* - config_name: por_Latn data_files: - split: test path: por_Latn/test-* - config_name: prs_Arab data_files: - split: test path: prs_Arab/test-* - config_name: quy_Latn data_files: - split: test path: quy_Latn/test-* - config_name: ron_Latn data_files: - split: test path: ron_Latn/test-* - config_name: run_Latn data_files: - split: test path: run_Latn/test-* - config_name: rus_Cyrl data_files: - split: test path: rus_Cyrl/test-* - config_name: sag_Latn data_files: - split: test path: sag_Latn/test-* - config_name: san_Deva data_files: - split: test path: san_Deva/test-* - config_name: sat_Olck data_files: - split: test path: sat_Olck/test-* - config_name: scn_Latn data_files: - split: test path: scn_Latn/test-* - config_name: shn_Mymr data_files: - split: test path: shn_Mymr/test-* - config_name: sin_Sinh data_files: - split: test path: sin_Sinh/test-* - config_name: slk_Latn data_files: - split: test path: slk_Latn/test-* - config_name: slv_Latn data_files: - split: test path: slv_Latn/test-* - config_name: smo_Latn data_files: - split: test path: smo_Latn/test-* - config_name: sna_Latn data_files: - split: test path: sna_Latn/test-* - config_name: snd_Arab data_files: - split: test path: snd_Arab/test-* - config_name: som_Latn data_files: - split: test path: som_Latn/test-* - config_name: sot_Latn data_files: - split: test path: sot_Latn/test-* - config_name: spa_Latn data_files: - split: test path: spa_Latn/test-* - config_name: srd_Latn data_files: - split: test path: srd_Latn/test-* - config_name: srp_Cyrl data_files: - split: test path: srp_Cyrl/test-* - config_name: ssw_Latn data_files: - split: test path: ssw_Latn/test-* - config_name: sun_Latn data_files: - split: test path: sun_Latn/test-* - config_name: swe_Latn data_files: - split: test path: swe_Latn/test-* - config_name: swh_Latn data_files: - split: test path: swh_Latn/test-* - config_name: szl_Latn data_files: - split: test path: szl_Latn/test-* - config_name: tam_Taml data_files: - split: test path: tam_Taml/test-* - config_name: taq_Latn data_files: - split: test path: taq_Latn/test-* - config_name: taq_Tfng data_files: - split: test path: taq_Tfng/test-* - config_name: tat_Cyrl data_files: - split: test path: tat_Cyrl/test-* - config_name: tel_Telu data_files: - split: test path: tel_Telu/test-* - config_name: tgk_Cyrl data_files: - split: test path: tgk_Cyrl/test-* - config_name: tgl_Latn data_files: - split: test path: tgl_Latn/test-* - config_name: tha_Thai data_files: - split: test path: tha_Thai/test-* - config_name: tir_Ethi data_files: - split: test path: tir_Ethi/test-* - config_name: tpi_Latn data_files: - split: test path: tpi_Latn/test-* - config_name: tsn_Latn data_files: - split: test path: tsn_Latn/test-* - config_name: tso_Latn data_files: - split: test path: tso_Latn/test-* - config_name: tuk_Latn data_files: - split: test path: tuk_Latn/test-* - config_name: tum_Latn data_files: - split: test path: tum_Latn/test-* - config_name: tur_Latn data_files: - split: test path: tur_Latn/test-* - config_name: twi_Latn data_files: - split: test path: twi_Latn/test-* - config_name: tzm_Tfng data_files: - split: test path: tzm_Tfng/test-* - config_name: uig_Arab data_files: - split: test path: uig_Arab/test-* - config_name: ukr_Cyrl data_files: - split: test path: ukr_Cyrl/test-* - config_name: umb_Latn data_files: - split: test path: umb_Latn/test-* - config_name: urd_Arab data_files: - split: test path: urd_Arab/test-* - config_name: uzn_Latn data_files: - split: test path: uzn_Latn/test-* - config_name: vec_Latn data_files: - split: test path: vec_Latn/test-* - config_name: vie_Latn data_files: - split: test path: vie_Latn/test-* - config_name: war_Latn data_files: - split: test path: war_Latn/test-* - config_name: wol_Latn data_files: - split: test path: wol_Latn/test-* - config_name: xho_Latn data_files: - split: test path: xho_Latn/test-* - config_name: ydd_Hebr data_files: - split: test path: ydd_Hebr/test-* - config_name: yor_Latn data_files: - split: test path: yor_Latn/test-* - config_name: yue_Hant data_files: - split: test path: yue_Hant/test-* - config_name: zho_Hans data_files: - split: test path: zho_Hans/test-* - config_name: zho_Hant data_files: - split: test path: zho_Hant/test-* - config_name: zsm_Latn data_files: - split: test path: zsm_Latn/test-* - config_name: zul_Latn data_files: - split: test path: zul_Latn/test-* ---

应用场景：