{"fineweb2": {"aai_Latn": ["data/aai_Latn/train/000_00000.parquet"], "aak_Latn": ["data/aak_Latn/train/000_00000.parquet"], "aau_Latn": ["data/aau_Latn/train/000_00000.parquet"], "aaz_Latn": ["data/aaz_Latn/train/000_00000.parquet"], "aba_Latn": ["data/aba_Latn/train/000_00000.parquet"], "abi_Latn": ["data/abi_Latn/train/000_00000.parquet"], "abk_Cyrl": ["data/abk_Cyrl/train/000_00000.parquet"], "abn_Latn": ["data/abn_Latn/train/000_00000.parquet"], "abq_Cyrl": ["data/abq_Cyrl/train/000_00000.parquet"], "abs_Latn": ["data/abs_Latn/train/000_00000.parquet"], "abt_Latn": ["data/abt_Latn/train/000_00000.parquet"], "abx_Latn": ["data/abx_Latn/train/000_00000.parquet"], "aby_Latn": ["data/aby_Latn/train/000_00000.parquet"], "abz_Latn": ["data/abz_Latn/train/000_00000.parquet"], "aca_Latn": ["data/aca_Latn/train/000_00000.parquet"], "acd_Latn": ["data/acd_Latn/train/000_00000.parquet"], "ace_Latn": ["data/ace_Latn/train/000_00000.parquet"], "acf_Latn": ["data/acf_Latn/train/000_00000.parquet"], "ach_Latn": ["data/ach_Latn/train/000_00000.parquet"], "acm_Arab": ["data/acm_Arab/train/000_00000.parquet"], "acn_Latn": ["data/acn_Latn/train/000_00000.parquet"], "acr_Latn": ["data/acr_Latn/train/000_00000.parquet"], "acu_Latn": ["data/acu_Latn/train/000_00000.parquet"], "ada_Latn": ["data/ada_Latn/train/000_00000.parquet"], "ade_Latn": ["data/ade_Latn/train/000_00000.parquet"], "adh_Latn": ["data/adh_Latn/train/000_00000.parquet"], "adi_Latn": ["data/adi_Latn/train/000_00000.parquet"], "adj_Latn": ["data/adj_Latn/train/000_00000.parquet"], "adl_Latn": ["data/adl_Latn/train/000_00000.parquet"], "ady_Cyrl": ["data/ady_Cyrl/train/000_00000.parquet"], "adz_Latn": ["data/adz_Latn/train/000_00000.parquet"], "aeb_Arab": ["data/aeb_Arab/train/000_00000.parquet"], "aer_Latn": ["data/aer_Latn/train/000_00000.parquet"], "aeu_Latn": ["data/aeu_Latn/train/000_00000.parquet"], "aey_Latn": ["data/aey_Latn/train/000_00000.parquet"], "afr_Latn": ["data/afr_Latn/train/000_00000.parquet"], "agd_Latn": ["data/agd_Latn/train/000_00000.parquet"], "agg_Latn": ["data/agg_Latn/train/000_00000.parquet"], "agm_Latn": ["data/agm_Latn/train/000_00000.parquet"], "agn_Latn": ["data/agn_Latn/train/000_00000.parquet"], "agr_Latn": ["data/agr_Latn/train/000_00000.parquet"], "agt_Latn": ["data/agt_Latn/train/000_00000.parquet"], "agu_Latn": ["data/agu_Latn/train/000_00000.parquet"], "agw_Latn": ["data/agw_Latn/train/000_00000.parquet"], "agx_Cyrl": ["data/agx_Cyrl/train/000_00000.parquet"], "aha_Latn": ["data/aha_Latn/train/000_00000.parquet"], "ahk_Latn": ["data/ahk_Latn/train/000_00000.parquet"], "aia_Latn": ["data/aia_Latn/train/000_00000.parquet"], "aii_Syrc": ["data/aii_Syrc/train/000_00000.parquet"], "aim_Latn": ["data/aim_Latn/train/000_00000.parquet"], "ain_Latn": ["data/ain_Latn/train/000_00000.parquet"], "ajg_Latn": ["data/ajg_Latn/train/000_00000.parquet"], "aji_Latn": ["data/aji_Latn/train/000_00000.parquet"], "ajz_Latn": ["data/ajz_Latn/train/000_00000.parquet"], "akb_Latn": ["data/akb_Latn/train/000_00000.parquet"], "ake_Latn": ["data/ake_Latn/train/000_00000.parquet"], "akh_Latn": ["data/akh_Latn/train/000_00000.parquet"], "akp_Latn": ["data/akp_Latn/train/000_00000.parquet"], "alj_Latn": ["data/alj_Latn/train/000_00000.parquet"], "aln_Latn": ["data/aln_Latn/train/000_00000.parquet"], "alp_Latn": ["data/alp_Latn/train/000_00000.parquet"], "alq_Latn": ["data/alq_Latn/train/000_00000.parquet"], "als_Latn": ["data/als_Latn/train/000_00000.parquet", "data/als_Latn/train/001_00000.parquet"], "alt_Cyrl": ["data/alt_Cyrl/train/000_00000.parquet"], "aly_Latn": ["data/aly_Latn/train/000_00000.parquet"], "alz_Latn": ["data/alz_Latn/train/000_00000.parquet"], "ame_Latn": ["data/ame_Latn/train/000_00000.parquet"], "amf_Latn": ["data/amf_Latn/train/000_00000.parquet"], "amh_Ethi": ["data/amh_Ethi/train/000_00000.parquet"], "ami_Latn": ["data/ami_Latn/train/000_00000.parquet"], "amk_Latn": ["data/amk_Latn/train/000_00000.parquet"], "amm_Latn": ["data/amm_Latn/train/000_00000.parquet"], "amn_Latn": ["data/amn_Latn/train/000_00000.parquet"], "amp_Latn": ["data/amp_Latn/train/000_00000.parquet"], "amr_Latn": ["data/amr_Latn/train/000_00000.parquet"], "amu_Latn": ["data/amu_Latn/train/000_00000.parquet"], "amx_Latn": ["data/amx_Latn/train/000_00000.parquet"], "ang_Latn": ["data/ang_Latn/train/000_00000.parquet"], "anm_Latn": ["data/anm_Latn/train/000_00000.parquet"], "ann_Latn": ["data/ann_Latn/train/000_00000.parquet"], "anp_Deva": ["data/anp_Deva/train/000_00000.parquet"], "anv_Latn": ["data/anv_Latn/train/000_00000.parquet"], "any_Latn": ["data/any_Latn/train/000_00000.parquet"], "aoi_Latn": ["data/aoi_Latn/train/000_00000.parquet"], "aoj_Latn": ["data/aoj_Latn/train/000_00000.parquet"], "aom_Latn": ["data/aom_Latn/train/000_00000.parquet"], "aoz_Latn": ["data/aoz_Latn/train/000_00000.parquet"], "apb_Latn": ["data/apb_Latn/train/000_00000.parquet"], "apc_Arab": ["data/apc_Arab/train/000_00000.parquet"], "ape_Latn": ["data/ape_Latn/train/000_00000.parquet"], "apn_Latn": ["data/apn_Latn/train/000_00000.parquet"], "apr_Latn": ["data/apr_Latn/train/000_00000.parquet"], "apt_Latn": ["data/apt_Latn/train/000_00000.parquet"], "apu_Latn": ["data/apu_Latn/train/000_00000.parquet"], "apw_Latn": ["data/apw_Latn/train/000_00000.parquet"], "apy_Latn": ["data/apy_Latn/train/000_00000.parquet"], "apz_Latn": ["data/apz_Latn/train/000_00000.parquet"], "arb_Arab": ["data/arb_Arab/train/000_00000.parquet", "data/arb_Arab/train/000_00001.parquet", "data/arb_Arab/train/000_00002.parquet"], "arb_Latn": ["data/arb_Latn/train/000_00000.parquet"], "are_Latn": ["data/are_Latn/train/000_00000.parquet"], "arg_Latn": ["data/arg_Latn/train/000_00000.parquet"], "arl_Latn": ["data/arl_Latn/train/000_00000.parquet"], "arn_Latn": ["data/arn_Latn/train/000_00000.parquet"], "arp_Latn": ["data/arp_Latn/train/000_00000.parquet"], "arq_Arab": ["data/arq_Arab/train/000_00000.parquet"], "ars_Arab": ["data/ars_Arab/train/000_00000.parquet"], "ary_Arab": ["data/ary_Arab/train/000_00000.parquet"], "arz_Arab": ["data/arz_Arab/train/000_00000.parquet"], "asg_Latn": ["data/asg_Latn/train/000_00000.parquet"], "asm_Beng": ["data/asm_Beng/train/000_00000.parquet"], "asm_Latn": ["data/asm_Latn/train/000_00000.parquet"], "aso_Latn": ["data/aso_Latn/train/000_00000.parquet"], "ast_Latn": ["data/ast_Latn/train/000_00000.parquet"], "ata_Latn": ["data/ata_Latn/train/000_00000.parquet"], "atb_Latn": ["data/atb_Latn/train/000_00000.parquet"], "atd_Latn": ["data/atd_Latn/train/000_00000.parquet"], "atg_Latn": ["data/atg_Latn/train/000_00000.parquet"], "ati_Latn": ["data/ati_Latn/train/000_00000.parquet"], "atj_Latn": ["data/atj_Latn/train/000_00000.parquet"], "atq_Latn": ["data/atq_Latn/train/000_00000.parquet"], "att_Latn": ["data/att_Latn/train/000_00000.parquet"], "auc_Latn": ["data/auc_Latn/train/000_00000.parquet"], "aui_Latn": ["data/aui_Latn/train/000_00000.parquet"], "auy_Latn": ["data/auy_Latn/train/000_00000.parquet"], "ava_Cyrl": ["data/ava_Cyrl/train/000_00000.parquet"], "avk_Latn": ["data/avk_Latn/train/000_00000.parquet"], "avn_Latn": ["data/avn_Latn/train/000_00000.parquet"], "avt_Latn": ["data/avt_Latn/train/000_00000.parquet"], "avu_Latn": ["data/avu_Latn/train/000_00000.parquet"], "awa_Deva": ["data/awa_Deva/train/000_00000.parquet"], "awb_Latn": ["data/awb_Latn/train/000_00000.parquet"], "awx_Latn": ["data/awx_Latn/train/000_00000.parquet"], "ayo_Latn": ["data/ayo_Latn/train/000_00000.parquet"], "ayp_Arab": ["data/ayp_Arab/train/000_00000.parquet"], "ayr_Latn": ["data/ayr_Latn/train/000_00000.parquet"], "azb_Arab": ["data/azb_Arab/train/000_00000.parquet"], "azg_Latn": ["data/azg_Latn/train/000_00000.parquet"], "azj_Cyrl": ["data/azj_Cyrl/train/000_00000.parquet"], "azj_Latn": ["data/azj_Latn/train/000_00000.parquet", "data/azj_Latn/train/001_00000.parquet", "data/azj_Latn/train/002_00000.parquet"], "azz_Latn": ["data/azz_Latn/train/000_00000.parquet"], "bak_Cyrl": ["data/bak_Cyrl/train/000_00000.parquet"], "bam_Latn": ["data/bam_Latn/train/000_00000.parquet"], "ban_Latn": ["data/ban_Latn/train/000_00000.parquet"], "bao_Latn": ["data/bao_Latn/train/000_00000.parquet"], "bar_Latn": ["data/bar_Latn/train/000_00000.parquet"], "bas_Latn": ["data/bas_Latn/train/000_00000.parquet"], "bav_Latn": ["data/bav_Latn/train/000_00000.parquet"], "bba_Latn": ["data/bba_Latn/train/000_00000.parquet"], "bbb_Latn": ["data/bbb_Latn/train/000_00000.parquet"], "bbc_Latn": ["data/bbc_Latn/train/000_00000.parquet"], "bbj_Latn": ["data/bbj_Latn/train/000_00000.parquet"], "bbk_Latn": ["data/bbk_Latn/train/000_00000.parquet"], "bbo_Latn": ["data/bbo_Latn/train/000_00000.parquet"], "bbr_Latn": ["data/bbr_Latn/train/000_00000.parquet"], "bch_Latn": ["data/bch_Latn/train/000_00000.parquet"], "bci_Latn": ["data/bci_Latn/train/000_00000.parquet"], "bcl_Latn": ["data/bcl_Latn/train/000_00000.parquet"], "bco_Latn": ["data/bco_Latn/train/000_00000.parquet"], "bcw_Latn": ["data/bcw_Latn/train/000_00000.parquet"], "bdd_Latn": ["data/bdd_Latn/train/000_00000.parquet"], "bdh_Latn": ["data/bdh_Latn/train/000_00000.parquet"], "bdq_Latn": ["data/bdq_Latn/train/000_00000.parquet"], "bea_Latn": ["data/bea_Latn/train/000_00000.parquet"], "bef_Latn": ["data/bef_Latn/train/000_00000.parquet"], "bel_Cyrl": ["data/bel_Cyrl/train/000_00000.parquet"], "bem_Latn": ["data/bem_Latn/train/000_00000.parquet"], "ben_Beng": ["data/ben_Beng/train/000_00000.parquet", "data/ben_Beng/train/001_00000.parquet", "data/ben_Beng/train/002_00000.parquet"], "ben_Latn": ["data/ben_Latn/train/000_00000.parquet"], "beq_Latn": ["data/beq_Latn/train/000_00000.parquet"], "bew_Latn": ["data/bew_Latn/train/000_00000.parquet"], "bex_Latn": ["data/bex_Latn/train/000_00000.parquet"], "bfd_Latn": ["data/bfd_Latn/train/000_00000.parquet"], "bfo_Latn": ["data/bfo_Latn/train/000_00000.parquet"], "bgr_Latn": ["data/bgr_Latn/train/000_00000.parquet"], "bgs_Latn": ["data/bgs_Latn/train/000_00000.parquet"], "bgt_Latn": ["data/bgt_Latn/train/000_00000.parquet"], "bgz_Latn": ["data/bgz_Latn/train/000_00000.parquet"], "bhg_Latn": ["data/bhg_Latn/train/000_00000.parquet"], "bhl_Latn": ["data/bhl_Latn/train/000_00000.parquet"], "bho_Deva": ["data/bho_Deva/train/000_00000.parquet"], "bhp_Latn": ["data/bhp_Latn/train/000_00000.parquet"], "bhw_Latn": ["data/bhw_Latn/train/000_00000.parquet"], "bhz_Latn": ["data/bhz_Latn/train/000_00000.parquet"], "bib_Latn": ["data/bib_Latn/train/000_00000.parquet"], "big_Latn": ["data/big_Latn/train/000_00000.parquet"], "bim_Latn": ["data/bim_Latn/train/000_00000.parquet"], "bin_Latn": ["data/bin_Latn/train/000_00000.parquet"], "bis_Latn": ["data/bis_Latn/train/000_00000.parquet"], "biu_Latn": ["data/biu_Latn/train/000_00000.parquet"], "biv_Latn": ["data/biv_Latn/train/000_00000.parquet"], "bjn_Arab": ["data/bjn_Arab/train/000_00000.parquet"], "bjn_Latn": ["data/bjn_Latn/train/000_00000.parquet"], "bjp_Latn": ["data/bjp_Latn/train/000_00000.parquet"], "bjr_Latn": ["data/bjr_Latn/train/000_00000.parquet"], "bjv_Latn": ["data/bjv_Latn/train/000_00000.parquet"], "bkd_Latn": ["data/bkd_Latn/train/000_00000.parquet"], "bkl_Latn": ["data/bkl_Latn/train/000_00000.parquet"], "bkq_Latn": ["data/bkq_Latn/train/000_00000.parquet"], "bku_Latn": ["data/bku_Latn/train/000_00000.parquet"], "bkv_Latn": ["data/bkv_Latn/train/000_00000.parquet"], "bla_Latn": ["data/bla_Latn/train/000_00000.parquet"], "blh_Latn": ["data/blh_Latn/train/000_00000.parquet"], "blk_Mymr": ["data/blk_Mymr/train/000_00000.parquet"], "blw_Latn": ["data/blw_Latn/train/000_00000.parquet"], "blz_Latn": ["data/blz_Latn/train/000_00000.parquet"], "bmh_Latn": ["data/bmh_Latn/train/000_00000.parquet"], "bmk_Latn": ["data/bmk_Latn/train/000_00000.parquet"], "bmq_Latn": ["data/bmq_Latn/train/000_00000.parquet"], "bmr_Latn": ["data/bmr_Latn/train/000_00000.parquet"], "bmu_Latn": ["data/bmu_Latn/train/000_00000.parquet"], "bmv_Latn": ["data/bmv_Latn/train/000_00000.parquet"], "bno_Latn": ["data/bno_Latn/train/000_00000.parquet"], "bnp_Latn": ["data/bnp_Latn/train/000_00000.parquet"], "boa_Latn": ["data/boa_Latn/train/000_00000.parquet"], "bod_Tibt": ["data/bod_Tibt/train/000_00000.parquet"], "boj_Latn": ["data/boj_Latn/train/000_00000.parquet"], "bom_Latn": ["data/bom_Latn/train/000_00000.parquet"], "bon_Latn": ["data/bon_Latn/train/000_00000.parquet"], "bos_Latn": ["data/bos_Latn/train/000_00000.parquet", "data/bos_Latn/train/001_00000.parquet", "data/bos_Latn/train/002_00000.parquet"], "bov_Latn": ["data/bov_Latn/train/000_00000.parquet"], "box_Latn": ["data/box_Latn/train/000_00000.parquet"], "bpr_Latn": ["data/bpr_Latn/train/000_00000.parquet"], "bps_Latn": ["data/bps_Latn/train/000_00000.parquet"], "bpy_Beng": ["data/bpy_Beng/train/000_00000.parquet"], "bqc_Latn": ["data/bqc_Latn/train/000_00000.parquet"], "bqj_Latn": ["data/bqj_Latn/train/000_00000.parquet"], "bqp_Latn": ["data/bqp_Latn/train/000_00000.parquet"], "bre_Latn": ["data/bre_Latn/train/000_00000.parquet"], "brh_Arab": ["data/brh_Arab/train/000_00000.parquet"], "bru_Latn": ["data/bru_Latn/train/000_00000.parquet"], "brx_Deva": ["data/brx_Deva/train/000_00000.parquet"], "bsc_Latn": ["data/bsc_Latn/train/000_00000.parquet"], "bsn_Latn": ["data/bsn_Latn/train/000_00000.parquet"], "bsp_Latn": ["data/bsp_Latn/train/000_00000.parquet"], "bsq_Latn": ["data/bsq_Latn/train/000_00000.parquet"], "bss_Latn": ["data/bss_Latn/train/000_00000.parquet"], "btd_Latn": ["data/btd_Latn/train/000_00000.parquet"], "bth_Latn": ["data/bth_Latn/train/000_00000.parquet"], "bts_Latn": ["data/bts_Latn/train/000_00000.parquet"], "btt_Latn": ["data/btt_Latn/train/000_00000.parquet"], "btx_Latn": ["data/btx_Latn/train/000_00000.parquet"], "bud_Latn": ["data/bud_Latn/train/000_00000.parquet"], "bug_Latn": ["data/bug_Latn/train/000_00000.parquet"], "buk_Latn": ["data/buk_Latn/train/000_00000.parquet"], "bul_Cyrl": ["data/bul_Cyrl/train/000_00000.parquet", "data/bul_Cyrl/train/000_00001.parquet", "data/bul_Cyrl/train/001_00000.parquet"], "bum_Latn": ["data/bum_Latn/train/000_00000.parquet"], "bus_Latn": ["data/bus_Latn/train/000_00000.parquet"], "bvc_Latn": ["data/bvc_Latn/train/000_00000.parquet"], "bvd_Latn": ["data/bvd_Latn/train/000_00000.parquet"], "bvr_Latn": ["data/bvr_Latn/train/000_00000.parquet"], "bvz_Latn": ["data/bvz_Latn/train/000_00000.parquet"], "bwd_Latn": ["data/bwd_Latn/train/000_00000.parquet"], "bwi_Latn": ["data/bwi_Latn/train/000_00000.parquet"], "bwq_Latn": ["data/bwq_Latn/train/000_00000.parquet"], "bwu_Latn": ["data/bwu_Latn/train/000_00000.parquet"], "bxh_Latn": ["data/bxh_Latn/train/000_00000.parquet"], "bxr_Cyrl": ["data/bxr_Cyrl/train/000_00000.parquet"], "byr_Latn": ["data/byr_Latn/train/000_00000.parquet"], "byv_Latn": ["data/byv_Latn/train/000_00000.parquet"], "byx_Latn": ["data/byx_Latn/train/000_00000.parquet"], "bzd_Latn": ["data/bzd_Latn/train/000_00000.parquet"], "bzh_Latn": ["data/bzh_Latn/train/000_00000.parquet"], "bzi_Thai": ["data/bzi_Thai/train/000_00000.parquet"], "bzj_Latn": ["data/bzj_Latn/train/000_00000.parquet"], "caa_Latn": ["data/caa_Latn/train/000_00000.parquet"], "cab_Latn": ["data/cab_Latn/train/000_00000.parquet"], "cac_Latn": ["data/cac_Latn/train/000_00000.parquet"], "caf_Latn": ["data/caf_Latn/train/000_00000.parquet"], "cag_Latn": ["data/cag_Latn/train/000_00000.parquet"], "cak_Latn": ["data/cak_Latn/train/000_00000.parquet"], "cao_Latn": ["data/cao_Latn/train/000_00000.parquet"], "cap_Latn": ["data/cap_Latn/train/000_00000.parquet"], "caq_Latn": ["data/caq_Latn/train/000_00000.parquet"], "car_Latn": ["data/car_Latn/train/000_00000.parquet"], "cas_Latn": ["data/cas_Latn/train/000_00000.parquet"], "cat_Latn": ["data/cat_Latn/train/000_00000.parquet", "data/cat_Latn/train/001_00000.parquet", "data/cat_Latn/train/002_00000.parquet"], "cav_Latn": ["data/cav_Latn/train/000_00000.parquet"], "cax_Latn": ["data/cax_Latn/train/000_00000.parquet"], "cbc_Latn": ["data/cbc_Latn/train/000_00000.parquet"], "cbi_Latn": ["data/cbi_Latn/train/000_00000.parquet"], "cbk_Latn": ["data/cbk_Latn/train/000_00000.parquet"], "cbr_Latn": ["data/cbr_Latn/train/000_00000.parquet"], "cbs_Latn": ["data/cbs_Latn/train/000_00000.parquet"], "cbt_Latn": ["data/cbt_Latn/train/000_00000.parquet"], "cbu_Latn": ["data/cbu_Latn/train/000_00000.parquet"], "cbv_Latn": ["data/cbv_Latn/train/000_00000.parquet"], "cce_Latn": ["data/cce_Latn/train/000_00000.parquet"], "cco_Latn": ["data/cco_Latn/train/000_00000.parquet"], "ccp_Latn": ["data/ccp_Latn/train/000_00000.parquet"], "ceb_Latn": ["data/ceb_Latn/train/000_00000.parquet"], "ceg_Latn": ["data/ceg_Latn/train/000_00000.parquet"], "cek_Latn": ["data/cek_Latn/train/000_00000.parquet"], "ces_Latn": ["data/ces_Latn/train/000_00000.parquet", "data/ces_Latn/train/000_00001.parquet", "data/ces_Latn/train/000_00002.parquet"], "cfm_Latn": ["data/cfm_Latn/train/000_00000.parquet"], "cgc_Latn": ["data/cgc_Latn/train/000_00000.parquet"], "cgg_Latn": ["data/cgg_Latn/train/000_00000.parquet"], "cha_Latn": ["data/cha_Latn/train/000_00000.parquet"], "chd_Latn": ["data/chd_Latn/train/000_00000.parquet"], "che_Cyrl": ["data/che_Cyrl/train/000_00000.parquet"], "chf_Latn": ["data/chf_Latn/train/000_00000.parquet"], "chj_Latn": ["data/chj_Latn/train/000_00000.parquet"], "chk_Latn": ["data/chk_Latn/train/000_00000.parquet"], "cho_Latn": ["data/cho_Latn/train/000_00000.parquet"], "chq_Latn": ["data/chq_Latn/train/000_00000.parquet"], "chr_Cher": ["data/chr_Cher/train/000_00000.parquet"], "chr_Latn": ["data/chr_Latn/train/000_00000.parquet"], "chu_Cyrl": ["data/chu_Cyrl/train/000_00000.parquet"], "chv_Cyrl": ["data/chv_Cyrl/train/000_00000.parquet"], "chw_Latn": ["data/chw_Latn/train/000_00000.parquet"], "chz_Latn": ["data/chz_Latn/train/000_00000.parquet"], "cjk_Latn": ["data/cjk_Latn/train/000_00000.parquet"], "cjo_Latn": ["data/cjo_Latn/train/000_00000.parquet"], "cjp_Latn": ["data/cjp_Latn/train/000_00000.parquet"], "cjs_Cyrl": ["data/cjs_Cyrl/train/000_00000.parquet"], "cjv_Latn": ["data/cjv_Latn/train/000_00000.parquet"], "ckb_Arab": ["data/ckb_Arab/train/000_00000.parquet"], "cko_Latn": ["data/cko_Latn/train/000_00000.parquet"], "ckt_Cyrl": ["data/ckt_Cyrl/train/000_00000.parquet"], "cle_Latn": ["data/cle_Latn/train/000_00000.parquet"], "clu_Latn": ["data/clu_Latn/train/000_00000.parquet"], "cly_Latn": ["data/cly_Latn/train/000_00000.parquet"], "cme_Latn": ["data/cme_Latn/train/000_00000.parquet"], "cmn_Hani": ["data/cmn_Hani/train/000_00000.parquet", "data/cmn_Hani/train/000_00001.parquet", "data/cmn_Hani/train/000_00002.parquet"], "cmo_Latn": ["data/cmo_Latn/train/000_00000.parquet"], "cmr_Latn": ["data/cmr_Latn/train/000_00000.parquet"], "cnh_Latn": ["data/cnh_Latn/train/000_00000.parquet"], "cni_Latn": ["data/cni_Latn/train/000_00000.parquet"], "cnk_Latn": ["data/cnk_Latn/train/000_00000.parquet"], "cnl_Latn": ["data/cnl_Latn/train/000_00000.parquet"], "cnt_Latn": ["data/cnt_Latn/train/000_00000.parquet"], "cnw_Latn": ["data/cnw_Latn/train/000_00000.parquet"], "coe_Latn": ["data/coe_Latn/train/000_00000.parquet"], "cof_Latn": ["data/cof_Latn/train/000_00000.parquet"], "cok_Latn": ["data/cok_Latn/train/000_00000.parquet"], "con_Latn": ["data/con_Latn/train/000_00000.parquet"], "cop_Copt": ["data/cop_Copt/train/000_00000.parquet"], "cor_Latn": ["data/cor_Latn/train/000_00000.parquet"], "cos_Latn": ["data/cos_Latn/train/000_00000.parquet"], "cot_Latn": ["data/cot_Latn/train/000_00000.parquet"], "cou_Latn": ["data/cou_Latn/train/000_00000.parquet"], "cpa_Latn": ["data/cpa_Latn/train/000_00000.parquet"], "cpb_Latn": ["data/cpb_Latn/train/000_00000.parquet"], "cpc_Latn": ["data/cpc_Latn/train/000_00000.parquet"], "cpu_Latn": ["data/cpu_Latn/train/000_00000.parquet"], "cpy_Latn": ["data/cpy_Latn/train/000_00000.parquet"], "crh_Cyrl": ["data/crh_Cyrl/train/000_00000.parquet"], "crh_Latn": ["data/crh_Latn/train/000_00000.parquet"], "crj_Cans": ["data/crj_Cans/train/000_00000.parquet"], "crk_Cans": ["data/crk_Cans/train/000_00000.parquet"], "crk_Latn": ["data/crk_Latn/train/000_00000.parquet"], "crl_Cans": ["data/crl_Cans/train/000_00000.parquet"], "crm_Cans": ["data/crm_Cans/train/000_00000.parquet"], "crn_Latn": ["data/crn_Latn/train/000_00000.parquet"], "crs_Latn": ["data/crs_Latn/train/000_00000.parquet"], "crt_Latn": ["data/crt_Latn/train/000_00000.parquet"], "crx_Latn": ["data/crx_Latn/train/000_00000.parquet"], "csb_Latn": ["data/csb_Latn/train/000_00000.parquet"], "csk_Latn": ["data/csk_Latn/train/000_00000.parquet"], "cso_Latn": ["data/cso_Latn/train/000_00000.parquet"], "csw_Latn": ["data/csw_Latn/train/000_00000.parquet"], "csy_Latn": ["data/csy_Latn/train/000_00000.parquet"], "cta_Latn": ["data/cta_Latn/train/000_00000.parquet"], "ctd_Latn": ["data/ctd_Latn/train/000_00000.parquet"], "cto_Latn": ["data/cto_Latn/train/000_00000.parquet"], "ctp_Latn": ["data/ctp_Latn/train/000_00000.parquet"], "ctu_Latn": ["data/ctu_Latn/train/000_00000.parquet"], "cub_Latn": ["data/cub_Latn/train/000_00000.parquet"], "cuc_Latn": ["data/cuc_Latn/train/000_00000.parquet"], "cui_Latn": ["data/cui_Latn/train/000_00000.parquet"], "cuk_Latn": ["data/cuk_Latn/train/000_00000.parquet"], "cul_Latn": ["data/cul_Latn/train/000_00000.parquet"], "cut_Latn": ["data/cut_Latn/train/000_00000.parquet"], "cux_Latn": ["data/cux_Latn/train/000_00000.parquet"], "cwe_Latn": ["data/cwe_Latn/train/000_00000.parquet"], "cwt_Latn": ["data/cwt_Latn/train/000_00000.parquet"], "cya_Latn": ["data/cya_Latn/train/000_00000.parquet"], "cym_Latn": ["data/cym_Latn/train/000_00000.parquet"], "czt_Latn": ["data/czt_Latn/train/000_00000.parquet"], "daa_Latn": ["data/daa_Latn/train/000_00000.parquet"], "dad_Latn": ["data/dad_Latn/train/000_00000.parquet"], "daf_Latn": ["data/daf_Latn/train/000_00000.parquet"], "dag_Latn": ["data/dag_Latn/train/000_00000.parquet"], "dah_Latn": ["data/dah_Latn/train/000_00000.parquet"], "dak_Latn": ["data/dak_Latn/train/000_00000.parquet"], "dan_Latn": ["data/dan_Latn/train/000_00000.parquet", "data/dan_Latn/train/000_00001.parquet", "data/dan_Latn/train/000_00002.parquet"], "dar_Cyrl": ["data/dar_Cyrl/train/000_00000.parquet"], "ddg_Latn": ["data/ddg_Latn/train/000_00000.parquet"], "ddn_Latn": ["data/ddn_Latn/train/000_00000.parquet"], "ded_Latn": ["data/ded_Latn/train/000_00000.parquet"], "des_Latn": ["data/des_Latn/train/000_00000.parquet"], "deu_Latn": ["data/deu_Latn/train/000_00000.parquet", "data/deu_Latn/train/000_00001.parquet", "data/deu_Latn/train/000_00002.parquet"], "dga_Latn": ["data/dga_Latn/train/000_00000.parquet"], "dgc_Latn": ["data/dgc_Latn/train/000_00000.parquet"], "dgi_Latn": ["data/dgi_Latn/train/000_00000.parquet"], "dgr_Latn": ["data/dgr_Latn/train/000_00000.parquet"], "dgz_Latn": ["data/dgz_Latn/train/000_00000.parquet"], "dhg_Latn": ["data/dhg_Latn/train/000_00000.parquet"], "dhm_Latn": ["data/dhm_Latn/train/000_00000.parquet"], "dhv_Latn": ["data/dhv_Latn/train/000_00000.parquet"], "did_Latn": ["data/did_Latn/train/000_00000.parquet"], "dig_Latn": ["data/dig_Latn/train/000_00000.parquet"], "dik_Latn": ["data/dik_Latn/train/000_00000.parquet"], "diq_Latn": ["data/diq_Latn/train/000_00000.parquet"], "dis_Latn": ["data/dis_Latn/train/000_00000.parquet"], "diu_Latn": ["data/diu_Latn/train/000_00000.parquet"], "div_Thaa": ["data/div_Thaa/train/000_00000.parquet"], "dje_Latn": ["data/dje_Latn/train/000_00000.parquet"], "djk_Latn": ["data/djk_Latn/train/000_00000.parquet"], "djr_Latn": ["data/djr_Latn/train/000_00000.parquet"], "dks_Latn": ["data/dks_Latn/train/000_00000.parquet"], "dln_Latn": ["data/dln_Latn/train/000_00000.parquet"], "dng_Cyrl": ["data/dng_Cyrl/train/000_00000.parquet"], "dnj_Latn": ["data/dnj_Latn/train/000_00000.parquet"], "dnw_Latn": ["data/dnw_Latn/train/000_00000.parquet"], "dob_Latn": ["data/dob_Latn/train/000_00000.parquet"], "doi_Deva": ["data/doi_Deva/train/000_00000.parquet"], "dop_Latn": ["data/dop_Latn/train/000_00000.parquet"], "dos_Latn": ["data/dos_Latn/train/000_00000.parquet"], "dow_Latn": ["data/dow_Latn/train/000_00000.parquet"], "drg_Latn": ["data/drg_Latn/train/000_00000.parquet"], "dru_Latn": ["data/dru_Latn/train/000_00000.parquet"], "dsb_Latn": ["data/dsb_Latn/train/000_00000.parquet"], "dtb_Latn": ["data/dtb_Latn/train/000_00000.parquet"], "dtp_Latn": ["data/dtp_Latn/train/000_00000.parquet"], "dts_Latn": ["data/dts_Latn/train/000_00000.parquet"], "dty_Deva": ["data/dty_Deva/train/000_00000.parquet"], "dua_Latn": ["data/dua_Latn/train/000_00000.parquet"], "due_Latn": ["data/due_Latn/train/000_00000.parquet"], "dug_Latn": ["data/dug_Latn/train/000_00000.parquet"], "duo_Latn": ["data/duo_Latn/train/000_00000.parquet"], "dur_Latn": ["data/dur_Latn/train/000_00000.parquet"], "dwr_Latn": ["data/dwr_Latn/train/000_00000.parquet"], "dww_Latn": ["data/dww_Latn/train/000_00000.parquet"], "dyi_Latn": ["data/dyi_Latn/train/000_00000.parquet"], "dyo_Latn": ["data/dyo_Latn/train/000_00000.parquet"], "dyu_Latn": ["data/dyu_Latn/train/000_00000.parquet"], "dzo_Tibt": ["data/dzo_Tibt/train/000_00000.parquet"], "ebk_Latn": ["data/ebk_Latn/train/000_00000.parquet"], "efi_Latn": ["data/efi_Latn/train/000_00000.parquet"], "eka_Latn": ["data/eka_Latn/train/000_00000.parquet"], "ekk_Latn": ["data/ekk_Latn/train/000_00000.parquet", "data/ekk_Latn/train/001_00000.parquet", "data/ekk_Latn/train/002_00000.parquet"], "eko_Latn": ["data/eko_Latn/train/000_00000.parquet"], "ell_Grek": ["data/ell_Grek/train/000_00000.parquet", "data/ell_Grek/train/000_00001.parquet", "data/ell_Grek/train/000_00002.parquet"], "emi_Latn": ["data/emi_Latn/train/000_00000.parquet"], "eml_Latn": ["data/eml_Latn/train/000_00000.parquet"], "emp_Latn": ["data/emp_Latn/train/000_00000.parquet"], "enb_Latn": ["data/enb_Latn/train/000_00000.parquet"], "enl_Latn": ["data/enl_Latn/train/000_00000.parquet"], "enm_Latn": ["data/enm_Latn/train/000_00000.parquet"], "enq_Latn": ["data/enq_Latn/train/000_00000.parquet"], "enx_Latn": ["data/enx_Latn/train/000_00000.parquet"], "epo_Latn": ["data/epo_Latn/train/000_00000.parquet"], "eri_Latn": ["data/eri_Latn/train/000_00000.parquet"], "ese_Latn": ["data/ese_Latn/train/000_00000.parquet"], "esi_Latn": ["data/esi_Latn/train/000_00000.parquet"], "esk_Latn": ["data/esk_Latn/train/000_00000.parquet"], "ess_Latn": ["data/ess_Latn/train/000_00000.parquet"], "esu_Latn": ["data/esu_Latn/train/000_00000.parquet"], "eto_Latn": ["data/eto_Latn/train/000_00000.parquet"], "etr_Latn": ["data/etr_Latn/train/000_00000.parquet"], "etu_Latn": ["data/etu_Latn/train/000_00000.parquet"], "eus_Latn": ["data/eus_Latn/train/000_00000.parquet"], "eve_Cyrl": ["data/eve_Cyrl/train/000_00000.parquet"], "ewe_Latn": ["data/ewe_Latn/train/000_00000.parquet"], "ewo_Latn": ["data/ewo_Latn/train/000_00000.parquet"], "ext_Latn": ["data/ext_Latn/train/000_00000.parquet"], "eza_Latn": ["data/eza_Latn/train/000_00000.parquet"], "faa_Latn": ["data/faa_Latn/train/000_00000.parquet"], "fad_Latn": ["data/fad_Latn/train/000_00000.parquet"], "fai_Latn": ["data/fai_Latn/train/000_00000.parquet"], "fal_Latn": ["data/fal_Latn/train/000_00000.parquet"], "fan_Latn": ["data/fan_Latn/train/000_00000.parquet"], "fao_Latn": ["data/fao_Latn/train/000_00000.parquet"], "far_Latn": ["data/far_Latn/train/000_00000.parquet"], "fas_Arab": ["data/fas_Arab/train/000_00000.parquet", "data/fas_Arab/train/000_00001.parquet", "data/fas_Arab/train/000_00002.parquet"], "fat_Latn": ["data/fat_Latn/train/000_00000.parquet"], "ffm_Latn": ["data/ffm_Latn/train/000_00000.parquet"], "fij_Latn": ["data/fij_Latn/train/000_00000.parquet"], "fil_Latn": ["data/fil_Latn/train/000_00000.parquet"], "fin_Latn": ["data/fin_Latn/train/000_00000.parquet", "data/fin_Latn/train/000_00001.parquet", "data/fin_Latn/train/000_00002.parquet"], "fit_Latn": ["data/fit_Latn/train/000_00000.parquet"], "fkv_Latn": ["data/fkv_Latn/train/000_00000.parquet"], "fmu_Deva": ["data/fmu_Deva/train/000_00000.parquet"], "fon_Latn": ["data/fon_Latn/train/000_00000.parquet"], "for_Latn": ["data/for_Latn/train/000_00000.parquet"], "fra_Latn": ["data/fra_Latn/train/000_00000.parquet", "data/fra_Latn/train/000_00001.parquet", "data/fra_Latn/train/000_00002.parquet"], "frd_Latn": ["data/frd_Latn/train/000_00000.parquet"], "fro_Latn": ["data/fro_Latn/train/000_00000.parquet"], "frp_Latn": ["data/frp_Latn/train/000_00000.parquet"], "frr_Latn": ["data/frr_Latn/train/000_00000.parquet"], "fry_Latn": ["data/fry_Latn/train/000_00000.parquet"], "fub_Latn": ["data/fub_Latn/train/000_00000.parquet"], "fud_Latn": ["data/fud_Latn/train/000_00000.parquet"], "fue_Latn": ["data/fue_Latn/train/000_00000.parquet"], "fuf_Latn": ["data/fuf_Latn/train/000_00000.parquet"], "fuh_Latn": ["data/fuh_Latn/train/000_00000.parquet"], "fuq_Latn": ["data/fuq_Latn/train/000_00000.parquet"], "fur_Latn": ["data/fur_Latn/train/000_00000.parquet"], "fuv_Arab": ["data/fuv_Arab/train/000_00000.parquet"], "fuv_Latn": ["data/fuv_Latn/train/000_00000.parquet"], "gaa_Latn": ["data/gaa_Latn/train/000_00000.parquet"], "gag_Cyrl": ["data/gag_Cyrl/train/000_00000.parquet"], "gag_Latn": ["data/gag_Latn/train/000_00000.parquet"], "gah_Latn": ["data/gah_Latn/train/000_00000.parquet"], "gai_Latn": ["data/gai_Latn/train/000_00000.parquet"], "gam_Latn": ["data/gam_Latn/train/000_00000.parquet"], "gaw_Latn": ["data/gaw_Latn/train/000_00000.parquet"], "gaz_Latn": ["data/gaz_Latn/train/000_00000.parquet"], "gbi_Latn": ["data/gbi_Latn/train/000_00000.parquet"], "gbo_Latn": ["data/gbo_Latn/train/000_00000.parquet"], "gbr_Latn": ["data/gbr_Latn/train/000_00000.parquet"], "gcf_Latn": ["data/gcf_Latn/train/000_00000.parquet"], "gcr_Latn": ["data/gcr_Latn/train/000_00000.parquet"], "gde_Latn": ["data/gde_Latn/train/000_00000.parquet"], "gdg_Latn": ["data/gdg_Latn/train/000_00000.parquet"], "gdn_Latn": ["data/gdn_Latn/train/000_00000.parquet"], "gdr_Latn": ["data/gdr_Latn/train/000_00000.parquet"], "geb_Latn": ["data/geb_Latn/train/000_00000.parquet"], "gej_Latn": ["data/gej_Latn/train/000_00000.parquet"], "gfk_Latn": ["data/gfk_Latn/train/000_00000.parquet"], "ghs_Latn": ["data/ghs_Latn/train/000_00000.parquet"], "gid_Latn": ["data/gid_Latn/train/000_00000.parquet"], "gil_Latn": ["data/gil_Latn/train/000_00000.parquet"], "giz_Latn": ["data/giz_Latn/train/000_00000.parquet"], "gjn_Latn": ["data/gjn_Latn/train/000_00000.parquet"], "gkn_Latn": ["data/gkn_Latn/train/000_00000.parquet"], "gla_Latn": ["data/gla_Latn/train/000_00000.parquet"], "gle_Latn": ["data/gle_Latn/train/000_00000.parquet"], "glg_Latn": ["data/glg_Latn/train/000_00000.parquet"], "glk_Arab": ["data/glk_Arab/train/000_00000.parquet"], "glv_Latn": ["data/glv_Latn/train/000_00000.parquet"], "gmh_Latn": ["data/gmh_Latn/train/000_00000.parquet"], "gmv_Ethi": ["data/gmv_Ethi/train/000_00000.parquet"], "gmv_Latn": ["data/gmv_Latn/train/000_00000.parquet"], "gna_Latn": ["data/gna_Latn/train/000_00000.parquet"], "gnb_Latn": ["data/gnb_Latn/train/000_00000.parquet"], "gnd_Latn": ["data/gnd_Latn/train/000_00000.parquet"], "gng_Latn": ["data/gng_Latn/train/000_00000.parquet"], "gnn_Latn": ["data/gnn_Latn/train/000_00000.parquet"], "gnw_Latn": ["data/gnw_Latn/train/000_00000.parquet"], "goa_Latn": ["data/goa_Latn/train/000_00000.parquet"], "gof_Ethi": ["data/gof_Ethi/train/000_00000.parquet"], "gof_Latn": ["data/gof_Latn/train/000_00000.parquet"], "gog_Latn": ["data/gog_Latn/train/000_00000.parquet"], "goh_Latn": ["data/goh_Latn/train/000_00000.parquet"], "gom_Deva": ["data/gom_Deva/train/000_00000.parquet"], "gom_Latn": ["data/gom_Latn/train/000_00000.parquet"], "gor_Latn": ["data/gor_Latn/train/000_00000.parquet"], "gos_Latn": ["data/gos_Latn/train/000_00000.parquet"], "got_Goth": ["data/got_Goth/train/000_00000.parquet"], "gqr_Latn": ["data/gqr_Latn/train/000_00000.parquet"], "grc_Grek": ["data/grc_Grek/train/000_00000.parquet"], "grt_Beng": ["data/grt_Beng/train/000_00000.parquet"], "gso_Latn": ["data/gso_Latn/train/000_00000.parquet"], "gsw_Latn": ["data/gsw_Latn/train/000_00000.parquet"], "gub_Latn": ["data/gub_Latn/train/000_00000.parquet"], "guc_Latn": ["data/guc_Latn/train/000_00000.parquet"], "gud_Latn": ["data/gud_Latn/train/000_00000.parquet"], "gug_Latn": ["data/gug_Latn/train/000_00000.parquet"], "guh_Latn": ["data/guh_Latn/train/000_00000.parquet"], "gui_Latn": ["data/gui_Latn/train/000_00000.parquet"], "guj_Gujr": ["data/guj_Gujr/train/000_00000.parquet"], "guj_Latn": ["data/guj_Latn/train/000_00000.parquet"], "guk_Ethi": ["data/guk_Ethi/train/000_00000.parquet"], "gul_Latn": ["data/gul_Latn/train/000_00000.parquet"], "gum_Latn": ["data/gum_Latn/train/000_00000.parquet"], "gun_Latn": ["data/gun_Latn/train/000_00000.parquet"], "guo_Latn": ["data/guo_Latn/train/000_00000.parquet"], "guq_Latn": ["data/guq_Latn/train/000_00000.parquet"], "gur_Latn": ["data/gur_Latn/train/000_00000.parquet"], "guu_Latn": ["data/guu_Latn/train/000_00000.parquet"], "guw_Latn": ["data/guw_Latn/train/000_00000.parquet"], "gux_Latn": ["data/gux_Latn/train/000_00000.parquet"], "guz_Latn": ["data/guz_Latn/train/000_00000.parquet"], "gvc_Latn": ["data/gvc_Latn/train/000_00000.parquet"], "gvf_Latn": ["data/gvf_Latn/train/000_00000.parquet"], "gvl_Latn": ["data/gvl_Latn/train/000_00000.parquet"], "gvn_Latn": ["data/gvn_Latn/train/000_00000.parquet"], "gwi_Latn": ["data/gwi_Latn/train/000_00000.parquet"], "gwr_Latn": ["data/gwr_Latn/train/000_00000.parquet"], "gya_Latn": ["data/gya_Latn/train/000_00000.parquet"], "gym_Latn": ["data/gym_Latn/train/000_00000.parquet"], "gyr_Latn": ["data/gyr_Latn/train/000_00000.parquet"], "hac_Arab": ["data/hac_Arab/train/000_00000.parquet"], "hae_Latn": ["data/hae_Latn/train/000_00000.parquet"], "hag_Latn": ["data/hag_Latn/train/000_00000.parquet"], "hak_Hani": ["data/hak_Hani/train/000_00000.parquet"], "hak_Latn": ["data/hak_Latn/train/000_00000.parquet"], "hat_Latn": ["data/hat_Latn/train/000_00000.parquet"], "hau_Latn": ["data/hau_Latn/train/000_00000.parquet"], "hav_Latn": ["data/hav_Latn/train/000_00000.parquet"], "haw_Latn": ["data/haw_Latn/train/000_00000.parquet"], "hay_Latn": ["data/hay_Latn/train/000_00000.parquet"], "hbo_Hebr": ["data/hbo_Hebr/train/000_00000.parquet"], "hch_Latn": ["data/hch_Latn/train/000_00000.parquet"], "heb_Hebr": ["data/heb_Hebr/train/000_00000.parquet", "data/heb_Hebr/train/001_00000.parquet", "data/heb_Hebr/train/002_00000.parquet"], "heg_Latn": ["data/heg_Latn/train/000_00000.parquet"], "heh_Latn": ["data/heh_Latn/train/000_00000.parquet"], "her_Latn": ["data/her_Latn/train/000_00000.parquet"], "hif_Latn": ["data/hif_Latn/train/000_00000.parquet"], "hig_Latn": ["data/hig_Latn/train/000_00000.parquet"], "hil_Latn": ["data/hil_Latn/train/000_00000.parquet"], "hin_Deva": ["data/hin_Deva/train/000_00000.parquet", "data/hin_Deva/train/001_00000.parquet", "data/hin_Deva/train/002_00000.parquet"], "hin_Latn": ["data/hin_Latn/train/000_00000.parquet"], "hix_Latn": ["data/hix_Latn/train/000_00000.parquet"], "hla_Latn": ["data/hla_Latn/train/000_00000.parquet"], "hmo_Latn": ["data/hmo_Latn/train/000_00000.parquet"], "hmr_Latn": ["data/hmr_Latn/train/000_00000.parquet"], "hne_Deva": ["data/hne_Deva/train/000_00000.parquet"], "hnj_Latn": ["data/hnj_Latn/train/000_00000.parquet"], "hnn_Latn": ["data/hnn_Latn/train/000_00000.parquet"], "hns_Latn": ["data/hns_Latn/train/000_00000.parquet"], "hop_Latn": ["data/hop_Latn/train/000_00000.parquet"], "hot_Latn": ["data/hot_Latn/train/000_00000.parquet"], "hra_Latn": ["data/hra_Latn/train/000_00000.parquet"], "hrv_Latn": ["data/hrv_Latn/train/000_00000.parquet", "data/hrv_Latn/train/001_00000.parquet", "data/hrv_Latn/train/002_00000.parquet"], "hrx_Latn": ["data/hrx_Latn/train/000_00000.parquet"], "hsb_Latn": ["data/hsb_Latn/train/000_00000.parquet"], "hto_Latn": ["data/hto_Latn/train/000_00000.parquet"], "hub_Latn": ["data/hub_Latn/train/000_00000.parquet"], "hui_Latn": ["data/hui_Latn/train/000_00000.parquet"], "hun_Latn": ["data/hun_Latn/train/000_00000.parquet", "data/hun_Latn/train/000_00001.parquet", "data/hun_Latn/train/000_00002.parquet"], "hus_Latn": ["data/hus_Latn/train/000_00000.parquet"], "huu_Latn": ["data/huu_Latn/train/000_00000.parquet"], "huv_Latn": ["data/huv_Latn/train/000_00000.parquet"], "hvn_Latn": ["data/hvn_Latn/train/000_00000.parquet"], "hwc_Latn": ["data/hwc_Latn/train/000_00000.parquet"], "hye_Armn": ["data/hye_Armn/train/000_00000.parquet"], "hyw_Armn": ["data/hyw_Armn/train/000_00000.parquet"], "ian_Latn": ["data/ian_Latn/train/000_00000.parquet"], "iba_Latn": ["data/iba_Latn/train/000_00000.parquet"], "ibg_Latn": ["data/ibg_Latn/train/000_00000.parquet"], "ibo_Latn": ["data/ibo_Latn/train/000_00000.parquet"], "icr_Latn": ["data/icr_Latn/train/000_00000.parquet"], "ido_Latn": ["data/ido_Latn/train/000_00000.parquet"], "idu_Latn": ["data/idu_Latn/train/000_00000.parquet"], "ifa_Latn": ["data/ifa_Latn/train/000_00000.parquet"], "ifb_Latn": ["data/ifb_Latn/train/000_00000.parquet"], "ife_Latn": ["data/ife_Latn/train/000_00000.parquet"], "ifk_Latn": ["data/ifk_Latn/train/000_00000.parquet"], "ifu_Latn": ["data/ifu_Latn/train/000_00000.parquet"], "ify_Latn": ["data/ify_Latn/train/000_00000.parquet"], "ige_Latn": ["data/ige_Latn/train/000_00000.parquet"], "ign_Latn": ["data/ign_Latn/train/000_00000.parquet"], "ike_Cans": ["data/ike_Cans/train/000_00000.parquet"], "ikk_Latn": ["data/ikk_Latn/train/000_00000.parquet"], "ikt_Latn": ["data/ikt_Latn/train/000_00000.parquet"], "ikw_Latn": ["data/ikw_Latn/train/000_00000.parquet"], "ilb_Latn": ["data/ilb_Latn/train/000_00000.parquet"], "ile_Latn": ["data/ile_Latn/train/000_00000.parquet"], "ilo_Latn": ["data/ilo_Latn/train/000_00000.parquet"], "imo_Latn": ["data/imo_Latn/train/000_00000.parquet"], "ina_Latn": ["data/ina_Latn/train/000_00000.parquet"], "inb_Latn": ["data/inb_Latn/train/000_00000.parquet"], "ind_Latn": ["data/ind_Latn/train/000_00000.parquet", "data/ind_Latn/train/000_00001.parquet", "data/ind_Latn/train/000_00002.parquet"], "inh_Cyrl": ["data/inh_Cyrl/train/000_00000.parquet"], "ino_Latn": ["data/ino_Latn/train/000_00000.parquet"], "iou_Latn": ["data/iou_Latn/train/000_00000.parquet"], "ipi_Latn": ["data/ipi_Latn/train/000_00000.parquet"], "iqw_Latn": ["data/iqw_Latn/train/000_00000.parquet"], "iri_Latn": ["data/iri_Latn/train/000_00000.parquet"], "irk_Latn": ["data/irk_Latn/train/000_00000.parquet"], "iry_Latn": ["data/iry_Latn/train/000_00000.parquet"], "isd_Latn": ["data/isd_Latn/train/000_00000.parquet"], "ish_Latn": ["data/ish_Latn/train/000_00000.parquet"], "isl_Latn": ["data/isl_Latn/train/000_00000.parquet", "data/isl_Latn/train/001_00000.parquet"], "iso_Latn": ["data/iso_Latn/train/000_00000.parquet"], "ita_Latn": ["data/ita_Latn/train/000_00000.parquet", "data/ita_Latn/train/000_00001.parquet", "data/ita_Latn/train/000_00002.parquet"], "itv_Latn": ["data/itv_Latn/train/000_00000.parquet"], "ium_Latn": ["data/ium_Latn/train/000_00000.parquet"], "ivb_Latn": ["data/ivb_Latn/train/000_00000.parquet"], "ivv_Latn": ["data/ivv_Latn/train/000_00000.parquet"], "iws_Latn": ["data/iws_Latn/train/000_00000.parquet"], "ixl_Latn": ["data/ixl_Latn/train/000_00000.parquet"], "izr_Latn": ["data/izr_Latn/train/000_00000.parquet"], "izz_Latn": ["data/izz_Latn/train/000_00000.parquet"], "jaa_Latn": ["data/jaa_Latn/train/000_00000.parquet"], "jac_Latn": ["data/jac_Latn/train/000_00000.parquet"], "jae_Latn": ["data/jae_Latn/train/000_00000.parquet"], "jam_Latn": ["data/jam_Latn/train/000_00000.parquet"], "jav_Latn": ["data/jav_Latn/train/000_00000.parquet"], "jbo_Latn": ["data/jbo_Latn/train/000_00000.parquet"], "jbu_Latn": ["data/jbu_Latn/train/000_00000.parquet"], "jic_Latn": ["data/jic_Latn/train/000_00000.parquet"], "jiv_Latn": ["data/jiv_Latn/train/000_00000.parquet"], "jmc_Latn": ["data/jmc_Latn/train/000_00000.parquet"], "jpn_Jpan": ["data/jpn_Jpan/train/000_00000.parquet", "data/jpn_Jpan/train/000_00001.parquet", "data/jpn_Jpan/train/000_00002.parquet"], "jra_Latn": ["data/jra_Latn/train/000_00000.parquet"], "jun_Orya": ["data/jun_Orya/train/000_00000.parquet"], "jvn_Latn": ["data/jvn_Latn/train/000_00000.parquet"], "kaa_Cyrl": ["data/kaa_Cyrl/train/000_00000.parquet"], "kaa_Latn": ["data/kaa_Latn/train/000_00000.parquet"], "kab_Latn": ["data/kab_Latn/train/000_00000.parquet"], "kac_Latn": ["data/kac_Latn/train/000_00000.parquet"], "kak_Latn": ["data/kak_Latn/train/000_00000.parquet"], "kal_Latn": ["data/kal_Latn/train/000_00000.parquet"], "kam_Latn": ["data/kam_Latn/train/000_00000.parquet"], "kan_Knda": ["data/kan_Knda/train/000_00000.parquet"], "kan_Latn": ["data/kan_Latn/train/000_00000.parquet"], "kao_Latn": ["data/kao_Latn/train/000_00000.parquet"], "kaq_Latn": ["data/kaq_Latn/train/000_00000.parquet"], "kas_Arab": ["data/kas_Arab/train/000_00000.parquet"], "kas_Deva": ["data/kas_Deva/train/000_00000.parquet"], "kas_Latn": ["data/kas_Latn/train/000_00000.parquet"], "kat_Geor": ["data/kat_Geor/train/000_00000.parquet", "data/kat_Geor/train/001_00000.parquet"], "kaz_Cyrl": ["data/kaz_Cyrl/train/000_00000.parquet", "data/kaz_Cyrl/train/001_00000.parquet"], "kbc_Latn": ["data/kbc_Latn/train/000_00000.parquet"], "kbd_Cyrl": ["data/kbd_Cyrl/train/000_00000.parquet"], "kbh_Latn": ["data/kbh_Latn/train/000_00000.parquet"], "kbm_Latn": ["data/kbm_Latn/train/000_00000.parquet"], "kbo_Latn": ["data/kbo_Latn/train/000_00000.parquet"], "kbp_Latn": ["data/kbp_Latn/train/000_00000.parquet"], "kbq_Latn": ["data/kbq_Latn/train/000_00000.parquet"], "kbr_Latn": ["data/kbr_Latn/train/000_00000.parquet"], "kby_Latn": ["data/kby_Latn/train/000_00000.parquet"], "kca_Cyrl": ["data/kca_Cyrl/train/000_00000.parquet"], "kcg_Latn": ["data/kcg_Latn/train/000_00000.parquet"], "kck_Latn": ["data/kck_Latn/train/000_00000.parquet"], "kdc_Latn": ["data/kdc_Latn/train/000_00000.parquet"], "kde_Latn": ["data/kde_Latn/train/000_00000.parquet"], "kdh_Latn": ["data/kdh_Latn/train/000_00000.parquet"], "kdi_Latn": ["data/kdi_Latn/train/000_00000.parquet"], "kdj_Latn": ["data/kdj_Latn/train/000_00000.parquet"], "kdl_Latn": ["data/kdl_Latn/train/000_00000.parquet"], "kdr_Latn": ["data/kdr_Latn/train/000_00000.parquet"], "kea_Latn": ["data/kea_Latn/train/000_00000.parquet"], "kei_Latn": ["data/kei_Latn/train/000_00000.parquet"], "kek_Latn": ["data/kek_Latn/train/000_00000.parquet"], "ken_Latn": ["data/ken_Latn/train/000_00000.parquet"], "keo_Latn": ["data/keo_Latn/train/000_00000.parquet"], "ker_Latn": ["data/ker_Latn/train/000_00000.parquet"], "kew_Latn": ["data/kew_Latn/train/000_00000.parquet"], "kez_Latn": ["data/kez_Latn/train/000_00000.parquet"], "kff_Telu": ["data/kff_Telu/train/000_00000.parquet"], "kgf_Latn": ["data/kgf_Latn/train/000_00000.parquet"], "kgk_Latn": ["data/kgk_Latn/train/000_00000.parquet"], "kgp_Latn": ["data/kgp_Latn/train/000_00000.parquet"], "kgr_Latn": ["data/kgr_Latn/train/000_00000.parquet"], "kha_Latn": ["data/kha_Latn/train/000_00000.parquet"], "khk_Cyrl": ["data/khk_Cyrl/train/000_00000.parquet"], "khm_Khmr": ["data/khm_Khmr/train/000_00000.parquet"], "khs_Latn": ["data/khs_Latn/train/000_00000.parquet"], "khz_Latn": ["data/khz_Latn/train/000_00000.parquet"], "kia_Latn": ["data/kia_Latn/train/000_00000.parquet"], "kij_Latn": ["data/kij_Latn/train/000_00000.parquet"], "kik_Latn": ["data/kik_Latn/train/000_00000.parquet"], "kin_Latn": ["data/kin_Latn/train/000_00000.parquet"], "kir_Cyrl": ["data/kir_Cyrl/train/000_00000.parquet"], "kiu_Latn": ["data/kiu_Latn/train/000_00000.parquet"], "kix_Latn": ["data/kix_Latn/train/000_00000.parquet"], "kjb_Latn": ["data/kjb_Latn/train/000_00000.parquet"], "kje_Latn": ["data/kje_Latn/train/000_00000.parquet"], "kjh_Cyrl": ["data/kjh_Cyrl/train/000_00000.parquet"], "kjs_Latn": ["data/kjs_Latn/train/000_00000.parquet"], "kkc_Latn": ["data/kkc_Latn/train/000_00000.parquet"], "kki_Latn": ["data/kki_Latn/train/000_00000.parquet"], "kkj_Latn": ["data/kkj_Latn/train/000_00000.parquet"], "kkl_Latn": ["data/kkl_Latn/train/000_00000.parquet"], "kle_Deva": ["data/kle_Deva/train/000_00000.parquet"], "klt_Latn": ["data/klt_Latn/train/000_00000.parquet"], "klv_Latn": ["data/klv_Latn/train/000_00000.parquet"], "kmb_Latn": ["data/kmb_Latn/train/000_00000.parquet"], "kmg_Latn": ["data/kmg_Latn/train/000_00000.parquet"], "kmh_Latn": ["data/kmh_Latn/train/000_00000.parquet"], "kmk_Latn": ["data/kmk_Latn/train/000_00000.parquet"], "kmm_Latn": ["data/kmm_Latn/train/000_00000.parquet"], "kmo_Latn": ["data/kmo_Latn/train/000_00000.parquet"], "kmr_Cyrl": ["data/kmr_Cyrl/train/000_00000.parquet"], "kmr_Latn": ["data/kmr_Latn/train/000_00000.parquet"], "kms_Latn": ["data/kms_Latn/train/000_00000.parquet"], "kmu_Latn": ["data/kmu_Latn/train/000_00000.parquet"], "kmy_Latn": ["data/kmy_Latn/train/000_00000.parquet"], "knc_Latn": ["data/knc_Latn/train/000_00000.parquet"], "kne_Latn": ["data/kne_Latn/train/000_00000.parquet"], "knf_Latn": ["data/knf_Latn/train/000_00000.parquet"], "kng_Latn": ["data/kng_Latn/train/000_00000.parquet"], "knj_Latn": ["data/knj_Latn/train/000_00000.parquet"], "knk_Latn": ["data/knk_Latn/train/000_00000.parquet"], "kno_Latn": ["data/kno_Latn/train/000_00000.parquet"], "knv_Latn": ["data/knv_Latn/train/000_00000.parquet"], "knx_Latn": ["data/knx_Latn/train/000_00000.parquet"], "kny_Latn": ["data/kny_Latn/train/000_00000.parquet"], "kog_Latn": ["data/kog_Latn/train/000_00000.parquet"], "koi_Cyrl": ["data/koi_Cyrl/train/000_00000.parquet"], "koo_Latn": ["data/koo_Latn/train/000_00000.parquet"], "kor_Hang": ["data/kor_Hang/train/000_00000.parquet", "data/kor_Hang/train/000_00001.parquet", "data/kor_Hang/train/000_00002.parquet"], "kos_Latn": ["data/kos_Latn/train/000_00000.parquet"], "kpe_Latn": ["data/kpe_Latn/train/000_00000.parquet"], "kpf_Latn": ["data/kpf_Latn/train/000_00000.parquet"], "kpg_Latn": ["data/kpg_Latn/train/000_00000.parquet"], "kpj_Latn": ["data/kpj_Latn/train/000_00000.parquet"], "kpq_Latn": ["data/kpq_Latn/train/000_00000.parquet"], "kpr_Latn": ["data/kpr_Latn/train/000_00000.parquet"], "kpv_Cyrl": ["data/kpv_Cyrl/train/000_00000.parquet"], "kpw_Latn": ["data/kpw_Latn/train/000_00000.parquet"], "kpx_Latn": ["data/kpx_Latn/train/000_00000.parquet"], "kpz_Latn": ["data/kpz_Latn/train/000_00000.parquet"], "kqc_Latn": ["data/kqc_Latn/train/000_00000.parquet"], "kqe_Latn": ["data/kqe_Latn/train/000_00000.parquet"], "kqf_Latn": ["data/kqf_Latn/train/000_00000.parquet"], "kql_Latn": ["data/kql_Latn/train/000_00000.parquet"], "kqn_Latn": ["data/kqn_Latn/train/000_00000.parquet"], "kqo_Latn": ["data/kqo_Latn/train/000_00000.parquet"], "kqp_Latn": ["data/kqp_Latn/train/000_00000.parquet"], "kqs_Latn": ["data/kqs_Latn/train/000_00000.parquet"], "kqw_Latn": ["data/kqw_Latn/train/000_00000.parquet"], "kqy_Ethi": ["data/kqy_Ethi/train/000_00000.parquet"], "krc_Cyrl": ["data/krc_Cyrl/train/000_00000.parquet"], "kri_Latn": ["data/kri_Latn/train/000_00000.parquet"], "krj_Latn": ["data/krj_Latn/train/000_00000.parquet"], "krl_Latn": ["data/krl_Latn/train/000_00000.parquet"], "kru_Deva": ["data/kru_Deva/train/000_00000.parquet"], "krx_Latn": ["data/krx_Latn/train/000_00000.parquet"], "ksb_Latn": ["data/ksb_Latn/train/000_00000.parquet"], "ksc_Latn": ["data/ksc_Latn/train/000_00000.parquet"], "ksd_Latn": ["data/ksd_Latn/train/000_00000.parquet"], "ksf_Latn": ["data/ksf_Latn/train/000_00000.parquet"], "ksh_Latn": ["data/ksh_Latn/train/000_00000.parquet"], "ksj_Latn": ["data/ksj_Latn/train/000_00000.parquet"], "ksp_Latn": ["data/ksp_Latn/train/000_00000.parquet"], "ksr_Latn": ["data/ksr_Latn/train/000_00000.parquet"], "kss_Latn": ["data/kss_Latn/train/000_00000.parquet"], "ksw_Mymr": ["data/ksw_Mymr/train/000_00000.parquet"], "ktb_Ethi": ["data/ktb_Ethi/train/000_00000.parquet"], "ktj_Latn": ["data/ktj_Latn/train/000_00000.parquet"], "ktm_Latn": ["data/ktm_Latn/train/000_00000.parquet"], "kto_Latn": ["data/kto_Latn/train/000_00000.parquet"], "ktu_Latn": ["data/ktu_Latn/train/000_00000.parquet"], "ktz_Latn": ["data/ktz_Latn/train/000_00000.parquet"], "kua_Latn": ["data/kua_Latn/train/000_00000.parquet"], "kub_Latn": ["data/kub_Latn/train/000_00000.parquet"], "kud_Latn": ["data/kud_Latn/train/000_00000.parquet"], "kue_Latn": ["data/kue_Latn/train/000_00000.parquet"], "kuj_Latn": ["data/kuj_Latn/train/000_00000.parquet"], "kum_Cyrl": ["data/kum_Cyrl/train/000_00000.parquet"], "kup_Latn": ["data/kup_Latn/train/000_00000.parquet"], "kus_Latn": ["data/kus_Latn/train/000_00000.parquet"], "kvg_Latn": ["data/kvg_Latn/train/000_00000.parquet"], "kvj_Latn": ["data/kvj_Latn/train/000_00000.parquet"], "kvn_Latn": ["data/kvn_Latn/train/000_00000.parquet"], "kwd_Latn": ["data/kwd_Latn/train/000_00000.parquet"], "kwf_Latn": ["data/kwf_Latn/train/000_00000.parquet"], "kwi_Latn": ["data/kwi_Latn/train/000_00000.parquet"], "kwj_Latn": ["data/kwj_Latn/train/000_00000.parquet"], "kwn_Latn": ["data/kwn_Latn/train/000_00000.parquet"], "kwy_Latn": ["data/kwy_Latn/train/000_00000.parquet"], "kxc_Ethi": ["data/kxc_Ethi/train/000_00000.parquet"], "kxm_Thai": ["data/kxm_Thai/train/000_00000.parquet"], "kxw_Latn": ["data/kxw_Latn/train/000_00000.parquet"], "kyc_Latn": ["data/kyc_Latn/train/000_00000.parquet"], "kyf_Latn": ["data/kyf_Latn/train/000_00000.parquet"], "kyg_Latn": ["data/kyg_Latn/train/000_00000.parquet"], "kyq_Latn": ["data/kyq_Latn/train/000_00000.parquet"], "kyu_Kali": ["data/kyu_Kali/train/000_00000.parquet"], "kyu_Latn": ["data/kyu_Latn/train/000_00000.parquet"], "kyu_Mymr": ["data/kyu_Mymr/train/000_00000.parquet"], "kyz_Latn": ["data/kyz_Latn/train/000_00000.parquet"], "kze_Latn": ["data/kze_Latn/train/000_00000.parquet"], "kzf_Latn": ["data/kzf_Latn/train/000_00000.parquet"], "kzj_Latn": ["data/kzj_Latn/train/000_00000.parquet"], "lac_Latn": ["data/lac_Latn/train/000_00000.parquet"], "lad_Hebr": ["data/lad_Hebr/train/000_00000.parquet"], "lad_Latn": ["data/lad_Latn/train/000_00000.parquet"], "lai_Latn": ["data/lai_Latn/train/000_00000.parquet"], "laj_Latn": ["data/laj_Latn/train/000_00000.parquet"], "lam_Latn": ["data/lam_Latn/train/000_00000.parquet"], "lao_Laoo": ["data/lao_Laoo/train/000_00000.parquet"], "lap_Latn": ["data/lap_Latn/train/000_00000.parquet"], "lat_Latn": ["data/lat_Latn/train/000_00000.parquet"], "lbb_Latn": ["data/lbb_Latn/train/000_00000.parquet"], "lbe_Cyrl": ["data/lbe_Cyrl/train/000_00000.parquet"], "lbj_Tibt": ["data/lbj_Tibt/train/000_00000.parquet"], "lbk_Latn": ["data/lbk_Latn/train/000_00000.parquet"], "lcm_Latn": ["data/lcm_Latn/train/000_00000.parquet"], "lcp_Thai": ["data/lcp_Thai/train/000_00000.parquet"], "ldi_Latn": ["data/ldi_Latn/train/000_00000.parquet"], "ldn_Latn": ["data/ldn_Latn/train/000_00000.parquet"], "lee_Latn": ["data/lee_Latn/train/000_00000.parquet"], "lef_Latn": ["data/lef_Latn/train/000_00000.parquet"], "leh_Latn": ["data/leh_Latn/train/000_00000.parquet"], "lem_Latn": ["data/lem_Latn/train/000_00000.parquet"], "leu_Latn": ["data/leu_Latn/train/000_00000.parquet"], "lew_Latn": ["data/lew_Latn/train/000_00000.parquet"], "lex_Latn": ["data/lex_Latn/train/000_00000.parquet"], "lez_Cyrl": ["data/lez_Cyrl/train/000_00000.parquet"], "lfn_Cyrl": ["data/lfn_Cyrl/train/000_00000.parquet"], "lfn_Latn": ["data/lfn_Latn/train/000_00000.parquet"], "lgg_Latn": ["data/lgg_Latn/train/000_00000.parquet"], "lgl_Latn": ["data/lgl_Latn/train/000_00000.parquet"], "lgm_Latn": ["data/lgm_Latn/train/000_00000.parquet"], "lhi_Latn": ["data/lhi_Latn/train/000_00000.parquet"], "lhu_Latn": ["data/lhu_Latn/train/000_00000.parquet"], "lia_Latn": ["data/lia_Latn/train/000_00000.parquet"], "lid_Latn": ["data/lid_Latn/train/000_00000.parquet"], "lif_Deva": ["data/lif_Deva/train/000_00000.parquet"], "lif_Limb": ["data/lif_Limb/train/000_00000.parquet"], "lij_Latn": ["data/lij_Latn/train/000_00000.parquet"], "lim_Latn": ["data/lim_Latn/train/000_00000.parquet"], "lin_Latn": ["data/lin_Latn/train/000_00000.parquet"], "lip_Latn": ["data/lip_Latn/train/000_00000.parquet"], "lis_Lisu": ["data/lis_Lisu/train/000_00000.parquet"], "lit_Latn": ["data/lit_Latn/train/000_00000.parquet", "data/lit_Latn/train/001_00000.parquet", "data/lit_Latn/train/002_00000.parquet"], "liv_Latn": ["data/liv_Latn/train/000_00000.parquet"], "ljp_Latn": ["data/ljp_Latn/train/000_00000.parquet"], "lki_Arab": ["data/lki_Arab/train/000_00000.parquet"], "llb_Latn": ["data/llb_Latn/train/000_00000.parquet"], "lld_Latn": ["data/lld_Latn/train/000_00000.parquet"], "llg_Latn": ["data/llg_Latn/train/000_00000.parquet"], "lln_Latn": ["data/lln_Latn/train/000_00000.parquet"], "lmk_Latn": ["data/lmk_Latn/train/000_00000.parquet"], "lmo_Latn": ["data/lmo_Latn/train/000_00000.parquet"], "lmp_Latn": ["data/lmp_Latn/train/000_00000.parquet"], "lnd_Latn": ["data/lnd_Latn/train/000_00000.parquet"], "lob_Latn": ["data/lob_Latn/train/000_00000.parquet"], "loe_Latn": ["data/loe_Latn/train/000_00000.parquet"], "log_Latn": ["data/log_Latn/train/000_00000.parquet"], "lok_Latn": ["data/lok_Latn/train/000_00000.parquet"], "lol_Latn": ["data/lol_Latn/train/000_00000.parquet"], "lom_Latn": ["data/lom_Latn/train/000_00000.parquet"], "loq_Latn": ["data/loq_Latn/train/000_00000.parquet"], "loz_Latn": ["data/loz_Latn/train/000_00000.parquet"], "lrc_Arab": ["data/lrc_Arab/train/000_00000.parquet"], "lsi_Latn": ["data/lsi_Latn/train/000_00000.parquet"], "lsm_Latn": ["data/lsm_Latn/train/000_00000.parquet"], "ltg_Latn": ["data/ltg_Latn/train/000_00000.parquet"], "ltz_Latn": ["data/ltz_Latn/train/000_00000.parquet"], "lua_Latn": ["data/lua_Latn/train/000_00000.parquet"], "lub_Latn": ["data/lub_Latn/train/000_00000.parquet"], "luc_Latn": ["data/luc_Latn/train/000_00000.parquet"], "lud_Latn": ["data/lud_Latn/train/000_00000.parquet"], "lue_Latn": ["data/lue_Latn/train/000_00000.parquet"], "lug_Latn": ["data/lug_Latn/train/000_00000.parquet"], "lun_Latn": ["data/lun_Latn/train/000_00000.parquet"], "luo_Latn": ["data/luo_Latn/train/000_00000.parquet"], "lus_Latn": ["data/lus_Latn/train/000_00000.parquet"], "lvs_Latn": ["data/lvs_Latn/train/000_00000.parquet", "data/lvs_Latn/train/001_00000.parquet", "data/lvs_Latn/train/002_00000.parquet"], "lwg_Latn": ["data/lwg_Latn/train/000_00000.parquet"], "lwo_Latn": ["data/lwo_Latn/train/000_00000.parquet"], "lww_Latn": ["data/lww_Latn/train/000_00000.parquet"], "lzh_Hani": ["data/lzh_Hani/train/000_00000.parquet"], "maa_Latn": ["data/maa_Latn/train/000_00000.parquet"], "mad_Latn": ["data/mad_Latn/train/000_00000.parquet"], "maf_Latn": ["data/maf_Latn/train/000_00000.parquet"], "mag_Deva": ["data/mag_Deva/train/000_00000.parquet"], "mah_Latn": ["data/mah_Latn/train/000_00000.parquet"], "mai_Deva": ["data/mai_Deva/train/000_00000.parquet"], "maj_Latn": ["data/maj_Latn/train/000_00000.parquet"], "mak_Latn": ["data/mak_Latn/train/000_00000.parquet"], "mal_Latn": ["data/mal_Latn/train/000_00000.parquet"], "mal_Mlym": ["data/mal_Mlym/train/000_00000.parquet", "data/mal_Mlym/train/001_00000.parquet"], "mam_Latn": ["data/mam_Latn/train/000_00000.parquet"], "maq_Latn": ["data/maq_Latn/train/000_00000.parquet"], "mar_Deva": ["data/mar_Deva/train/000_00000.parquet", "data/mar_Deva/train/001_00000.parquet"], "mar_Latn": ["data/mar_Latn/train/000_00000.parquet"], "mas_Latn": ["data/mas_Latn/train/000_00000.parquet"], "mau_Latn": ["data/mau_Latn/train/000_00000.parquet"], "mav_Latn": ["data/mav_Latn/train/000_00000.parquet"], "maw_Latn": ["data/maw_Latn/train/000_00000.parquet"], "maz_Latn": ["data/maz_Latn/train/000_00000.parquet"], "mbb_Latn": ["data/mbb_Latn/train/000_00000.parquet"], "mbc_Latn": ["data/mbc_Latn/train/000_00000.parquet"], "mbd_Latn": ["data/mbd_Latn/train/000_00000.parquet"], "mbf_Latn": ["data/mbf_Latn/train/000_00000.parquet"], "mbh_Latn": ["data/mbh_Latn/train/000_00000.parquet"], "mbi_Latn": ["data/mbi_Latn/train/000_00000.parquet"], "mbj_Latn": ["data/mbj_Latn/train/000_00000.parquet"], "mbl_Latn": ["data/mbl_Latn/train/000_00000.parquet"], "mbs_Latn": ["data/mbs_Latn/train/000_00000.parquet"], "mbt_Latn": ["data/mbt_Latn/train/000_00000.parquet"], "mca_Latn": ["data/mca_Latn/train/000_00000.parquet"], "mcb_Latn": ["data/mcb_Latn/train/000_00000.parquet"], "mcd_Latn": ["data/mcd_Latn/train/000_00000.parquet"], "mcf_Latn": ["data/mcf_Latn/train/000_00000.parquet"], "mck_Latn": ["data/mck_Latn/train/000_00000.parquet"], "mcn_Latn": ["data/mcn_Latn/train/000_00000.parquet"], "mco_Latn": ["data/mco_Latn/train/000_00000.parquet"], "mcp_Latn": ["data/mcp_Latn/train/000_00000.parquet"], "mcq_Latn": ["data/mcq_Latn/train/000_00000.parquet"], "mcu_Latn": ["data/mcu_Latn/train/000_00000.parquet"], "mda_Latn": ["data/mda_Latn/train/000_00000.parquet"], "mdf_Cyrl": ["data/mdf_Cyrl/train/000_00000.parquet"], "mdy_Ethi": ["data/mdy_Ethi/train/000_00000.parquet"], "med_Latn": ["data/med_Latn/train/000_00000.parquet"], "mee_Latn": ["data/mee_Latn/train/000_00000.parquet"], "mej_Latn": ["data/mej_Latn/train/000_00000.parquet"], "mek_Latn": ["data/mek_Latn/train/000_00000.parquet"], "men_Latn": ["data/men_Latn/train/000_00000.parquet"], "meq_Latn": ["data/meq_Latn/train/000_00000.parquet"], "mer_Latn": ["data/mer_Latn/train/000_00000.parquet"], "met_Latn": ["data/met_Latn/train/000_00000.parquet"], "meu_Latn": ["data/meu_Latn/train/000_00000.parquet"], "mev_Latn": ["data/mev_Latn/train/000_00000.parquet"], "mfe_Latn": ["data/mfe_Latn/train/000_00000.parquet"], "mfg_Latn": ["data/mfg_Latn/train/000_00000.parquet"], "mfh_Latn": ["data/mfh_Latn/train/000_00000.parquet"], "mfi_Latn": ["data/mfi_Latn/train/000_00000.parquet"], "mfk_Latn": ["data/mfk_Latn/train/000_00000.parquet"], "mfq_Latn": ["data/mfq_Latn/train/000_00000.parquet"], "mfy_Latn": ["data/mfy_Latn/train/000_00000.parquet"], "mfz_Latn": ["data/mfz_Latn/train/000_00000.parquet"], "mgc_Latn": ["data/mgc_Latn/train/000_00000.parquet"], "mgh_Latn": ["data/mgh_Latn/train/000_00000.parquet"], "mgo_Latn": ["data/mgo_Latn/train/000_00000.parquet"], "mgr_Latn": ["data/mgr_Latn/train/000_00000.parquet"], "mhi_Latn": ["data/mhi_Latn/train/000_00000.parquet"], "mhl_Latn": ["data/mhl_Latn/train/000_00000.parquet"], "mhr_Cyrl": ["data/mhr_Cyrl/train/000_00000.parquet"], "mhw_Latn": ["data/mhw_Latn/train/000_00000.parquet"], "mhx_Latn": ["data/mhx_Latn/train/000_00000.parquet"], "mhy_Latn": ["data/mhy_Latn/train/000_00000.parquet"], "mib_Latn": ["data/mib_Latn/train/000_00000.parquet"], "mic_Latn": ["data/mic_Latn/train/000_00000.parquet"], "mie_Latn": ["data/mie_Latn/train/000_00000.parquet"], "mif_Latn": ["data/mif_Latn/train/000_00000.parquet"], "mig_Latn": ["data/mig_Latn/train/000_00000.parquet"], "mih_Latn": ["data/mih_Latn/train/000_00000.parquet"], "mil_Latn": ["data/mil_Latn/train/000_00000.parquet"], "mim_Latn": ["data/mim_Latn/train/000_00000.parquet"], "min_Latn": ["data/min_Latn/train/000_00000.parquet"], "mio_Latn": ["data/mio_Latn/train/000_00000.parquet"], "mip_Latn": ["data/mip_Latn/train/000_00000.parquet"], "miq_Latn": ["data/miq_Latn/train/000_00000.parquet"], "mir_Latn": ["data/mir_Latn/train/000_00000.parquet"], "mit_Latn": ["data/mit_Latn/train/000_00000.parquet"], "miy_Latn": ["data/miy_Latn/train/000_00000.parquet"], "miz_Latn": ["data/miz_Latn/train/000_00000.parquet"], "mjc_Latn": ["data/mjc_Latn/train/000_00000.parquet"], "mjw_Latn": ["data/mjw_Latn/train/000_00000.parquet"], "mkd_Cyrl": ["data/mkd_Cyrl/train/000_00000.parquet", "data/mkd_Cyrl/train/001_00000.parquet"], "mkl_Latn": ["data/mkl_Latn/train/000_00000.parquet"], "mkn_Latn": ["data/mkn_Latn/train/000_00000.parquet"], "mks_Latn": ["data/mks_Latn/train/000_00000.parquet"], "mkz_Latn": ["data/mkz_Latn/train/000_00000.parquet"], "mlh_Latn": ["data/mlh_Latn/train/000_00000.parquet"], "mlp_Latn": ["data/mlp_Latn/train/000_00000.parquet"], "mlt_Latn": ["data/mlt_Latn/train/000_00000.parquet"], "mlu_Latn": ["data/mlu_Latn/train/000_00000.parquet"], "mmn_Latn": ["data/mmn_Latn/train/000_00000.parquet"], "mmo_Latn": ["data/mmo_Latn/train/000_00000.parquet"], "mmx_Latn": ["data/mmx_Latn/train/000_00000.parquet"], "mna_Latn": ["data/mna_Latn/train/000_00000.parquet"], "mnb_Latn": ["data/mnb_Latn/train/000_00000.parquet"], "mnf_Latn": ["data/mnf_Latn/train/000_00000.parquet"], "mni_Beng": ["data/mni_Beng/train/000_00000.parquet"], "mni_Latn": ["data/mni_Latn/train/000_00000.parquet"], "mni_Mtei": ["data/mni_Mtei/train/000_00000.parquet"], "mnk_Latn": ["data/mnk_Latn/train/000_00000.parquet"], "mns_Cyrl": ["data/mns_Cyrl/train/000_00000.parquet"], "mnw_Mymr": ["data/mnw_Mymr/train/000_00000.parquet"], "mnx_Latn": ["data/mnx_Latn/train/000_00000.parquet"], "mny_Latn": ["data/mny_Latn/train/000_00000.parquet"], "moa_Latn": ["data/moa_Latn/train/000_00000.parquet"], "moc_Latn": ["data/moc_Latn/train/000_00000.parquet"], "mog_Latn": ["data/mog_Latn/train/000_00000.parquet"], "moh_Latn": ["data/moh_Latn/train/000_00000.parquet"], "mop_Latn": ["data/mop_Latn/train/000_00000.parquet"], "mor_Latn": ["data/mor_Latn/train/000_00000.parquet"], "mos_Latn": ["data/mos_Latn/train/000_00000.parquet"], "mox_Latn": ["data/mox_Latn/train/000_00000.parquet"], "mpg_Latn": ["data/mpg_Latn/train/000_00000.parquet"], "mph_Latn": ["data/mph_Latn/train/000_00000.parquet"], "mpm_Latn": ["data/mpm_Latn/train/000_00000.parquet"], "mpp_Latn": ["data/mpp_Latn/train/000_00000.parquet"], "mps_Latn": ["data/mps_Latn/train/000_00000.parquet"], "mpt_Latn": ["data/mpt_Latn/train/000_00000.parquet"], "mpx_Latn": ["data/mpx_Latn/train/000_00000.parquet"], "mqb_Latn": ["data/mqb_Latn/train/000_00000.parquet"], "mqj_Latn": ["data/mqj_Latn/train/000_00000.parquet"], "mqy_Latn": ["data/mqy_Latn/train/000_00000.parquet"], "mrg_Latn": ["data/mrg_Latn/train/000_00000.parquet"], "mri_Latn": ["data/mri_Latn/train/000_00000.parquet"], "mrj_Cyrl": ["data/mrj_Cyrl/train/000_00000.parquet"], "mrq_Latn": ["data/mrq_Latn/train/000_00000.parquet"], "mrv_Latn": ["data/mrv_Latn/train/000_00000.parquet"], "mrw_Latn": ["data/mrw_Latn/train/000_00000.parquet"], "msb_Latn": ["data/msb_Latn/train/000_00000.parquet"], "msc_Latn": ["data/msc_Latn/train/000_00000.parquet"], "mse_Latn": ["data/mse_Latn/train/000_00000.parquet"], "msk_Latn": ["data/msk_Latn/train/000_00000.parquet"], "msy_Latn": ["data/msy_Latn/train/000_00000.parquet"], "mta_Latn": ["data/mta_Latn/train/000_00000.parquet"], "mtg_Latn": ["data/mtg_Latn/train/000_00000.parquet"], "mti_Latn": ["data/mti_Latn/train/000_00000.parquet"], "mto_Latn": ["data/mto_Latn/train/000_00000.parquet"], "mtp_Latn": ["data/mtp_Latn/train/000_00000.parquet"], "mua_Latn": ["data/mua_Latn/train/000_00000.parquet"], "mug_Latn": ["data/mug_Latn/train/000_00000.parquet"], "muh_Latn": ["data/muh_Latn/train/000_00000.parquet"], "mui_Latn": ["data/mui_Latn/train/000_00000.parquet"], "mup_Deva": ["data/mup_Deva/train/000_00000.parquet"], "mur_Latn": ["data/mur_Latn/train/000_00000.parquet"], "mus_Latn": ["data/mus_Latn/train/000_00000.parquet"], "mux_Latn": ["data/mux_Latn/train/000_00000.parquet"], "muy_Latn": ["data/muy_Latn/train/000_00000.parquet"], "mva_Latn": ["data/mva_Latn/train/000_00000.parquet"], "mvn_Latn": ["data/mvn_Latn/train/000_00000.parquet"], "mvp_Latn": ["data/mvp_Latn/train/000_00000.parquet"], "mwc_Latn": ["data/mwc_Latn/train/000_00000.parquet"], "mwf_Latn": ["data/mwf_Latn/train/000_00000.parquet"], "mwl_Latn": ["data/mwl_Latn/train/000_00000.parquet"], "mwm_Latn": ["data/mwm_Latn/train/000_00000.parquet"], "mwn_Latn": ["data/mwn_Latn/train/000_00000.parquet"], "mwp_Latn": ["data/mwp_Latn/train/000_00000.parquet"], "mwq_Latn": ["data/mwq_Latn/train/000_00000.parquet"], "mwv_Latn": ["data/mwv_Latn/train/000_00000.parquet"], "mww_Latn": ["data/mww_Latn/train/000_00000.parquet"], "mxb_Latn": ["data/mxb_Latn/train/000_00000.parquet"], "mxp_Latn": ["data/mxp_Latn/train/000_00000.parquet"], "mxq_Latn": ["data/mxq_Latn/train/000_00000.parquet"], "mxt_Latn": ["data/mxt_Latn/train/000_00000.parquet"], "mxv_Latn": ["data/mxv_Latn/train/000_00000.parquet"], "mya_Mymr": ["data/mya_Mymr/train/000_00000.parquet"], "myb_Latn": ["data/myb_Latn/train/000_00000.parquet"], "myk_Latn": ["data/myk_Latn/train/000_00000.parquet"], "myu_Latn": ["data/myu_Latn/train/000_00000.parquet"], "myv_Cyrl": ["data/myv_Cyrl/train/000_00000.parquet"], "myw_Latn": ["data/myw_Latn/train/000_00000.parquet"], "myx_Latn": ["data/myx_Latn/train/000_00000.parquet"], "myy_Latn": ["data/myy_Latn/train/000_00000.parquet"], "mza_Latn": ["data/mza_Latn/train/000_00000.parquet"], "mzh_Latn": ["data/mzh_Latn/train/000_00000.parquet"], "mzk_Latn": ["data/mzk_Latn/train/000_00000.parquet"], "mzl_Latn": ["data/mzl_Latn/train/000_00000.parquet"], "mzm_Latn": ["data/mzm_Latn/train/000_00000.parquet"], "mzn_Arab": ["data/mzn_Arab/train/000_00000.parquet"], "mzw_Latn": ["data/mzw_Latn/train/000_00000.parquet"], "mzz_Latn": ["data/mzz_Latn/train/000_00000.parquet"], "nab_Latn": ["data/nab_Latn/train/000_00000.parquet"], "naf_Latn": ["data/naf_Latn/train/000_00000.parquet"], "nah_Latn": ["data/nah_Latn/train/000_00000.parquet"], "nak_Latn": ["data/nak_Latn/train/000_00000.parquet"], "nan_Latn": ["data/nan_Latn/train/000_00000.parquet"], "nap_Latn": ["data/nap_Latn/train/000_00000.parquet"], "naq_Latn": ["data/naq_Latn/train/000_00000.parquet"], "nas_Latn": ["data/nas_Latn/train/000_00000.parquet"], "nav_Latn": ["data/nav_Latn/train/000_00000.parquet"], "naw_Latn": ["data/naw_Latn/train/000_00000.parquet"], "nba_Latn": ["data/nba_Latn/train/000_00000.parquet"], "nbc_Latn": ["data/nbc_Latn/train/000_00000.parquet"], "nbe_Latn": ["data/nbe_Latn/train/000_00000.parquet"], "nbl_Latn": ["data/nbl_Latn/train/000_00000.parquet"], "nbq_Latn": ["data/nbq_Latn/train/000_00000.parquet"], "nbu_Latn": ["data/nbu_Latn/train/000_00000.parquet"], "nca_Latn": ["data/nca_Latn/train/000_00000.parquet"], "nch_Latn": ["data/nch_Latn/train/000_00000.parquet"], "ncj_Latn": ["data/ncj_Latn/train/000_00000.parquet"], "ncl_Latn": ["data/ncl_Latn/train/000_00000.parquet"], "ncq_Laoo": ["data/ncq_Laoo/train/000_00000.parquet"], "nct_Latn": ["data/nct_Latn/train/000_00000.parquet"], "ncu_Latn": ["data/ncu_Latn/train/000_00000.parquet"], "ncx_Latn": ["data/ncx_Latn/train/000_00000.parquet"], "ndc_Latn": ["data/ndc_Latn/train/000_00000.parquet"], "nde_Latn": ["data/nde_Latn/train/000_00000.parquet"], "ndh_Latn": ["data/ndh_Latn/train/000_00000.parquet"], "ndi_Latn": ["data/ndi_Latn/train/000_00000.parquet"], "ndj_Latn": ["data/ndj_Latn/train/000_00000.parquet"], "ndo_Latn": ["data/ndo_Latn/train/000_00000.parquet"], "nds_Latn": ["data/nds_Latn/train/000_00000.parquet"], "ndz_Latn": ["data/ndz_Latn/train/000_00000.parquet"], "neb_Latn": ["data/neb_Latn/train/000_00000.parquet"], "new_Deva": ["data/new_Deva/train/000_00000.parquet"], "nfa_Latn": ["data/nfa_Latn/train/000_00000.parquet"], "nfr_Latn": ["data/nfr_Latn/train/000_00000.parquet"], "ngb_Latn": ["data/ngb_Latn/train/000_00000.parquet"], "ngc_Latn": ["data/ngc_Latn/train/000_00000.parquet"], "ngl_Latn": ["data/ngl_Latn/train/000_00000.parquet"], "ngp_Latn": ["data/ngp_Latn/train/000_00000.parquet"], "ngu_Latn": ["data/ngu_Latn/train/000_00000.parquet"], "nhd_Latn": ["data/nhd_Latn/train/000_00000.parquet"], "nhe_Latn": ["data/nhe_Latn/train/000_00000.parquet"], "nhg_Latn": ["data/nhg_Latn/train/000_00000.parquet"], "nhi_Latn": ["data/nhi_Latn/train/000_00000.parquet"], "nhk_Latn": ["data/nhk_Latn/train/000_00000.parquet"], "nho_Latn": ["data/nho_Latn/train/000_00000.parquet"], "nhr_Latn": ["data/nhr_Latn/train/000_00000.parquet"], "nhu_Latn": ["data/nhu_Latn/train/000_00000.parquet"], "nhw_Latn": ["data/nhw_Latn/train/000_00000.parquet"], "nhx_Latn": ["data/nhx_Latn/train/000_00000.parquet"], "nhy_Latn": ["data/nhy_Latn/train/000_00000.parquet"], "nia_Latn": ["data/nia_Latn/train/000_00000.parquet"], "nif_Latn": ["data/nif_Latn/train/000_00000.parquet"], "nii_Latn": ["data/nii_Latn/train/000_00000.parquet"], "nij_Latn": ["data/nij_Latn/train/000_00000.parquet"], "nim_Latn": ["data/nim_Latn/train/000_00000.parquet"], "nin_Latn": ["data/nin_Latn/train/000_00000.parquet"], "nio_Cyrl": ["data/nio_Cyrl/train/000_00000.parquet"], "niu_Latn": ["data/niu_Latn/train/000_00000.parquet"], "niy_Latn": ["data/niy_Latn/train/000_00000.parquet"], "njb_Latn": ["data/njb_Latn/train/000_00000.parquet"], "njm_Latn": ["data/njm_Latn/train/000_00000.parquet"], "njn_Latn": ["data/njn_Latn/train/000_00000.parquet"], "njo_Latn": ["data/njo_Latn/train/000_00000.parquet"], "njz_Latn": ["data/njz_Latn/train/000_00000.parquet"], "nkf_Latn": ["data/nkf_Latn/train/000_00000.parquet"], "nko_Latn": ["data/nko_Latn/train/000_00000.parquet"], "nld_Latn": ["data/nld_Latn/train/000_00000.parquet", "data/nld_Latn/train/000_00001.parquet", "data/nld_Latn/train/000_00002.parquet"], "nlg_Latn": ["data/nlg_Latn/train/000_00000.parquet"], "nma_Latn": ["data/nma_Latn/train/000_00000.parquet"], "nmf_Latn": ["data/nmf_Latn/train/000_00000.parquet"], "nmh_Latn": ["data/nmh_Latn/train/000_00000.parquet"], "nmo_Latn": ["data/nmo_Latn/train/000_00000.parquet"], "nmw_Latn": ["data/nmw_Latn/train/000_00000.parquet"], "nmz_Latn": ["data/nmz_Latn/train/000_00000.parquet"], "nnb_Latn": ["data/nnb_Latn/train/000_00000.parquet"], "nng_Latn": ["data/nng_Latn/train/000_00000.parquet"], "nnh_Latn": ["data/nnh_Latn/train/000_00000.parquet"], "nnl_Latn": ["data/nnl_Latn/train/000_00000.parquet"], "nno_Latn": ["data/nno_Latn/train/000_00000.parquet"], "nnp_Latn": ["data/nnp_Latn/train/000_00000.parquet"], "nnq_Latn": ["data/nnq_Latn/train/000_00000.parquet"], "nnw_Latn": ["data/nnw_Latn/train/000_00000.parquet"], "noa_Latn": ["data/noa_Latn/train/000_00000.parquet"], "nob_Latn": ["data/nob_Latn/train/000_00000.parquet", "data/nob_Latn/train/000_00001.parquet", "data/nob_Latn/train/000_00002.parquet"], "nod_Thai": ["data/nod_Thai/train/000_00000.parquet"], "nog_Cyrl": ["data/nog_Cyrl/train/000_00000.parquet"], "non_Latn": ["data/non_Latn/train/000_00000.parquet"], "nop_Latn": ["data/nop_Latn/train/000_00000.parquet"], "not_Latn": ["data/not_Latn/train/000_00000.parquet"], "nou_Latn": ["data/nou_Latn/train/000_00000.parquet"], "nov_Latn": ["data/nov_Latn/train/000_00000.parquet"], "nph_Latn": ["data/nph_Latn/train/000_00000.parquet"], "npi_Deva": ["data/npi_Deva/train/000_00000.parquet", "data/npi_Deva/train/001_00000.parquet"], "npi_Latn": ["data/npi_Latn/train/000_00000.parquet"], "npl_Latn": ["data/npl_Latn/train/000_00000.parquet"], "npo_Latn": ["data/npo_Latn/train/000_00000.parquet"], "npy_Latn": ["data/npy_Latn/train/000_00000.parquet"], "nqo_Nkoo": ["data/nqo_Nkoo/train/000_00000.parquet"], "nre_Latn": ["data/nre_Latn/train/000_00000.parquet"], "nrf_Latn": ["data/nrf_Latn/train/000_00000.parquet"], "nri_Latn": ["data/nri_Latn/train/000_00000.parquet"], "nrm_Latn": ["data/nrm_Latn/train/000_00000.parquet"], "nsa_Latn": ["data/nsa_Latn/train/000_00000.parquet"], "nse_Latn": ["data/nse_Latn/train/000_00000.parquet"], "nsm_Latn": ["data/nsm_Latn/train/000_00000.parquet"], "nsn_Latn": ["data/nsn_Latn/train/000_00000.parquet"], "nso_Latn": ["data/nso_Latn/train/000_00000.parquet"], "nss_Latn": ["data/nss_Latn/train/000_00000.parquet"], "nst_Latn": ["data/nst_Latn/train/000_00000.parquet"], "nsu_Latn": ["data/nsu_Latn/train/000_00000.parquet"], "ntp_Latn": ["data/ntp_Latn/train/000_00000.parquet"], "ntr_Latn": ["data/ntr_Latn/train/000_00000.parquet"], "ntu_Latn": ["data/ntu_Latn/train/000_00000.parquet"], "nuj_Latn": ["data/nuj_Latn/train/000_00000.parquet"], "nus_Latn": ["data/nus_Latn/train/000_00000.parquet"], "nuy_Latn": ["data/nuy_Latn/train/000_00000.parquet"], "nvm_Latn": ["data/nvm_Latn/train/000_00000.parquet"], "nwb_Latn": ["data/nwb_Latn/train/000_00000.parquet"], "nwi_Latn": ["data/nwi_Latn/train/000_00000.parquet"], "nwx_Deva": ["data/nwx_Deva/train/000_00000.parquet"], "nxd_Latn": ["data/nxd_Latn/train/000_00000.parquet"], "nya_Latn": ["data/nya_Latn/train/000_00000.parquet"], "nyf_Latn": ["data/nyf_Latn/train/000_00000.parquet"], "nyk_Latn": ["data/nyk_Latn/train/000_00000.parquet"], "nyn_Latn": ["data/nyn_Latn/train/000_00000.parquet"], "nyo_Latn": ["data/nyo_Latn/train/000_00000.parquet"], "nyu_Latn": ["data/nyu_Latn/train/000_00000.parquet"], "nyy_Latn": ["data/nyy_Latn/train/000_00000.parquet"], "nza_Latn": ["data/nza_Latn/train/000_00000.parquet"], "nzi_Latn": ["data/nzi_Latn/train/000_00000.parquet"], "nzm_Latn": ["data/nzm_Latn/train/000_00000.parquet"], "obo_Latn": ["data/obo_Latn/train/000_00000.parquet"], "oci_Latn": ["data/oci_Latn/train/000_00000.parquet"], "ogo_Latn": ["data/ogo_Latn/train/000_00000.parquet"], "ojb_Cans": ["data/ojb_Cans/train/000_00000.parquet"], "ojb_Latn": ["data/ojb_Latn/train/000_00000.parquet"], "oke_Latn": ["data/oke_Latn/train/000_00000.parquet"], "oku_Latn": ["data/oku_Latn/train/000_00000.parquet"], "okv_Latn": ["data/okv_Latn/train/000_00000.parquet"], "old_Latn": ["data/old_Latn/train/000_00000.parquet"], "olo_Latn": ["data/olo_Latn/train/000_00000.parquet"], "omb_Latn": ["data/omb_Latn/train/000_00000.parquet"], "omw_Latn": ["data/omw_Latn/train/000_00000.parquet"], "ong_Latn": ["data/ong_Latn/train/000_00000.parquet"], "ons_Latn": ["data/ons_Latn/train/000_00000.parquet"], "ood_Latn": ["data/ood_Latn/train/000_00000.parquet"], "opm_Latn": ["data/opm_Latn/train/000_00000.parquet"], "orv_Cyrl": ["data/orv_Cyrl/train/000_00000.parquet"], "ory_Latn": ["data/ory_Latn/train/000_00000.parquet"], "ory_Orya": ["data/ory_Orya/train/000_00000.parquet"], "oss_Cyrl": ["data/oss_Cyrl/train/000_00000.parquet"], "ota_Arab": ["data/ota_Arab/train/000_00000.parquet"], "otd_Latn": ["data/otd_Latn/train/000_00000.parquet"], "ote_Latn": ["data/ote_Latn/train/000_00000.parquet"], "otm_Latn": ["data/otm_Latn/train/000_00000.parquet"], "otn_Latn": ["data/otn_Latn/train/000_00000.parquet"], "oto_Latn": ["data/oto_Latn/train/000_00000.parquet"], "otq_Latn": ["data/otq_Latn/train/000_00000.parquet"], "ots_Latn": ["data/ots_Latn/train/000_00000.parquet"], "otw_Latn": ["data/otw_Latn/train/000_00000.parquet"], "oym_Latn": ["data/oym_Latn/train/000_00000.parquet"], "ozm_Latn": ["data/ozm_Latn/train/000_00000.parquet"], "pab_Latn": ["data/pab_Latn/train/000_00000.parquet"], "pad_Latn": ["data/pad_Latn/train/000_00000.parquet"], "pag_Latn": ["data/pag_Latn/train/000_00000.parquet"], "pah_Latn": ["data/pah_Latn/train/000_00000.parquet"], "pam_Latn": ["data/pam_Latn/train/000_00000.parquet"], "pan_Guru": ["data/pan_Guru/train/000_00000.parquet"], "pan_Latn": ["data/pan_Latn/train/000_00000.parquet"], "pao_Latn": ["data/pao_Latn/train/000_00000.parquet"], "pap_Latn": ["data/pap_Latn/train/000_00000.parquet"], "pau_Latn": ["data/pau_Latn/train/000_00000.parquet"], "pbb_Latn": ["data/pbb_Latn/train/000_00000.parquet"], "pbc_Latn": ["data/pbc_Latn/train/000_00000.parquet"], "pbi_Latn": ["data/pbi_Latn/train/000_00000.parquet"], "pbt_Arab": ["data/pbt_Arab/train/000_00000.parquet"], "pcd_Latn": ["data/pcd_Latn/train/000_00000.parquet"], "pck_Latn": ["data/pck_Latn/train/000_00000.parquet"], "pcm_Latn": ["data/pcm_Latn/train/000_00000.parquet"], "pdc_Latn": ["data/pdc_Latn/train/000_00000.parquet"], "pdt_Latn": ["data/pdt_Latn/train/000_00000.parquet"], "pem_Latn": ["data/pem_Latn/train/000_00000.parquet"], "pfe_Latn": ["data/pfe_Latn/train/000_00000.parquet"], "pfl_Latn": ["data/pfl_Latn/train/000_00000.parquet"], "phm_Latn": ["data/phm_Latn/train/000_00000.parquet"], "pib_Latn": ["data/pib_Latn/train/000_00000.parquet"], "pio_Latn": ["data/pio_Latn/train/000_00000.parquet"], "pir_Latn": ["data/pir_Latn/train/000_00000.parquet"], "pis_Latn": ["data/pis_Latn/train/000_00000.parquet"], "pjt_Latn": ["data/pjt_Latn/train/000_00000.parquet"], "pkb_Latn": ["data/pkb_Latn/train/000_00000.parquet"], "plg_Latn": ["data/plg_Latn/train/000_00000.parquet"], "pls_Latn": ["data/pls_Latn/train/000_00000.parquet"], "plt_Latn": ["data/plt_Latn/train/000_00000.parquet"], "plu_Latn": ["data/plu_Latn/train/000_00000.parquet"], "plw_Latn": ["data/plw_Latn/train/000_00000.parquet"], "pma_Latn": ["data/pma_Latn/train/000_00000.parquet"], "pmf_Latn": ["data/pmf_Latn/train/000_00000.parquet"], "pmq_Latn": ["data/pmq_Latn/train/000_00000.parquet"], "pms_Latn": ["data/pms_Latn/train/000_00000.parquet"], "pmx_Latn": ["data/pmx_Latn/train/000_00000.parquet"], "pnb_Arab": ["data/pnb_Arab/train/000_00000.parquet"], "pne_Latn": ["data/pne_Latn/train/000_00000.parquet"], "pnt_Grek": ["data/pnt_Grek/train/000_00000.parquet"], "pny_Latn": ["data/pny_Latn/train/000_00000.parquet"], "poe_Latn": ["data/poe_Latn/train/000_00000.parquet"], "poh_Latn": ["data/poh_Latn/train/000_00000.parquet"], "poi_Latn": ["data/poi_Latn/train/000_00000.parquet"], "pol_Latn": ["data/pol_Latn/train/000_00000.parquet", "data/pol_Latn/train/000_00001.parquet", "data/pol_Latn/train/000_00002.parquet"], "pon_Latn": ["data/pon_Latn/train/000_00000.parquet"], "por_Latn": ["data/por_Latn/train/000_00000.parquet", "data/por_Latn/train/000_00001.parquet", "data/por_Latn/train/000_00002.parquet"], "pos_Latn": ["data/pos_Latn/train/000_00000.parquet"], "pot_Latn": ["data/pot_Latn/train/000_00000.parquet"], "pov_Latn": ["data/pov_Latn/train/000_00000.parquet"], "poy_Latn": ["data/poy_Latn/train/000_00000.parquet"], "ppk_Latn": ["data/ppk_Latn/train/000_00000.parquet"], "ppo_Latn": ["data/ppo_Latn/train/000_00000.parquet"], "pps_Latn": ["data/pps_Latn/train/000_00000.parquet"], "prf_Latn": ["data/prf_Latn/train/000_00000.parquet"], "prg_Latn": ["data/prg_Latn/train/000_00000.parquet"], "pri_Latn": ["data/pri_Latn/train/000_00000.parquet"], "prq_Latn": ["data/prq_Latn/train/000_00000.parquet"], "pse_Latn": ["data/pse_Latn/train/000_00000.parquet"], "pss_Latn": ["data/pss_Latn/train/000_00000.parquet"], "ptp_Latn": ["data/ptp_Latn/train/000_00000.parquet"], "ptu_Latn": ["data/ptu_Latn/train/000_00000.parquet"], "pui_Latn": ["data/pui_Latn/train/000_00000.parquet"], "pwg_Latn": ["data/pwg_Latn/train/000_00000.parquet"], "pwn_Latn": ["data/pwn_Latn/train/000_00000.parquet"], "pww_Thai": ["data/pww_Thai/train/000_00000.parquet"], "pxm_Latn": ["data/pxm_Latn/train/000_00000.parquet"], "qub_Latn": ["data/qub_Latn/train/000_00000.parquet"], "quc_Latn": ["data/quc_Latn/train/000_00000.parquet"], "quf_Latn": ["data/quf_Latn/train/000_00000.parquet"], "qug_Latn": ["data/qug_Latn/train/000_00000.parquet"], "quh_Latn": ["data/quh_Latn/train/000_00000.parquet"], "qul_Latn": ["data/qul_Latn/train/000_00000.parquet"], "qup_Latn": ["data/qup_Latn/train/000_00000.parquet"], "qus_Latn": ["data/qus_Latn/train/000_00000.parquet"], "quw_Latn": ["data/quw_Latn/train/000_00000.parquet"], "quy_Latn": ["data/quy_Latn/train/000_00000.parquet"], "quz_Latn": ["data/quz_Latn/train/000_00000.parquet"], "qva_Latn": ["data/qva_Latn/train/000_00000.parquet"], "qvc_Latn": ["data/qvc_Latn/train/000_00000.parquet"], "qve_Latn": ["data/qve_Latn/train/000_00000.parquet"], "qvh_Latn": ["data/qvh_Latn/train/000_00000.parquet"], "qvi_Latn": ["data/qvi_Latn/train/000_00000.parquet"], "qvm_Latn": ["data/qvm_Latn/train/000_00000.parquet"], "qvn_Latn": ["data/qvn_Latn/train/000_00000.parquet"], "qvo_Latn": ["data/qvo_Latn/train/000_00000.parquet"], "qvs_Latn": ["data/qvs_Latn/train/000_00000.parquet"], "qvw_Latn": ["data/qvw_Latn/train/000_00000.parquet"], "qvz_Latn": ["data/qvz_Latn/train/000_00000.parquet"], "qwh_Latn": ["data/qwh_Latn/train/000_00000.parquet"], "qxh_Latn": ["data/qxh_Latn/train/000_00000.parquet"], "qxl_Latn": ["data/qxl_Latn/train/000_00000.parquet"], "qxn_Latn": ["data/qxn_Latn/train/000_00000.parquet"], "qxo_Latn": ["data/qxo_Latn/train/000_00000.parquet"], "qxr_Latn": ["data/qxr_Latn/train/000_00000.parquet"], "rad_Latn": ["data/rad_Latn/train/000_00000.parquet"], "rai_Latn": ["data/rai_Latn/train/000_00000.parquet"], "rap_Latn": ["data/rap_Latn/train/000_00000.parquet"], "rar_Latn": ["data/rar_Latn/train/000_00000.parquet"], "rav_Deva": ["data/rav_Deva/train/000_00000.parquet"], "raw_Latn": ["data/raw_Latn/train/000_00000.parquet"], "rcf_Latn": ["data/rcf_Latn/train/000_00000.parquet"], "rej_Latn": ["data/rej_Latn/train/000_00000.parquet"], "rel_Latn": ["data/rel_Latn/train/000_00000.parquet"], "rgu_Latn": ["data/rgu_Latn/train/000_00000.parquet"], "rhg_Latn": ["data/rhg_Latn/train/000_00000.parquet"], "ria_Latn": ["data/ria_Latn/train/000_00000.parquet"], "rim_Latn": ["data/rim_Latn/train/000_00000.parquet"], "rjs_Deva": ["data/rjs_Deva/train/000_00000.parquet"], "rkb_Latn": ["data/rkb_Latn/train/000_00000.parquet"], "rmc_Latn": ["data/rmc_Latn/train/000_00000.parquet"], "rme_Latn": ["data/rme_Latn/train/000_00000.parquet"], "rml_Latn": ["data/rml_Latn/train/000_00000.parquet"], "rmn_Cyrl": ["data/rmn_Cyrl/train/000_00000.parquet"], "rmn_Grek": ["data/rmn_Grek/train/000_00000.parquet"], "rmn_Latn": ["data/rmn_Latn/train/000_00000.parquet"], "rmo_Latn": ["data/rmo_Latn/train/000_00000.parquet"], "rmq_Latn": ["data/rmq_Latn/train/000_00000.parquet"], "rmy_Cyrl": ["data/rmy_Cyrl/train/000_00000.parquet"], "rmy_Latn": ["data/rmy_Latn/train/000_00000.parquet"], "rnd_Latn": ["data/rnd_Latn/train/000_00000.parquet"], "rng_Latn": ["data/rng_Latn/train/000_00000.parquet"], "rnl_Latn": ["data/rnl_Latn/train/000_00000.parquet"], "roh_Latn": ["data/roh_Latn/train/000_00000.parquet"], "ron_Cyrl": ["data/ron_Cyrl/train/000_00000.parquet"], "ron_Latn": ["data/ron_Latn/train/000_00000.parquet", "data/ron_Latn/train/000_00001.parquet", "data/ron_Latn/train/000_00002.parquet"], "roo_Latn": ["data/roo_Latn/train/000_00000.parquet"], "rop_Latn": ["data/rop_Latn/train/000_00000.parquet"], "row_Latn": ["data/row_Latn/train/000_00000.parquet"], "rro_Latn": ["data/rro_Latn/train/000_00000.parquet"], "rtm_Latn": ["data/rtm_Latn/train/000_00000.parquet"], "rub_Latn": ["data/rub_Latn/train/000_00000.parquet"], "rue_Cyrl": ["data/rue_Cyrl/train/000_00000.parquet"], "ruf_Latn": ["data/ruf_Latn/train/000_00000.parquet"], "rug_Latn": ["data/rug_Latn/train/000_00000.parquet"], "run_Latn": ["data/run_Latn/train/000_00000.parquet"], "rup_Latn": ["data/rup_Latn/train/000_00000.parquet"], "rus_Cyrl": ["data/rus_Cyrl/train/000_00000.parquet", "data/rus_Cyrl/train/000_00001.parquet", "data/rus_Cyrl/train/000_00002.parquet"], "rwo_Latn": ["data/rwo_Latn/train/000_00000.parquet"], "sab_Latn": ["data/sab_Latn/train/000_00000.parquet"], "sag_Latn": ["data/sag_Latn/train/000_00000.parquet"], "sah_Cyrl": ["data/sah_Cyrl/train/000_00000.parquet"], "san_Deva": ["data/san_Deva/train/000_00000.parquet"], "san_Latn": ["data/san_Latn/train/000_00000.parquet"], "sas_Latn": ["data/sas_Latn/train/000_00000.parquet"], "sat_Latn": ["data/sat_Latn/train/000_00000.parquet"], "sat_Olck": ["data/sat_Olck/train/000_00000.parquet"], "sba_Latn": ["data/sba_Latn/train/000_00000.parquet"], "sbd_Latn": ["data/sbd_Latn/train/000_00000.parquet"], "sbe_Latn": ["data/sbe_Latn/train/000_00000.parquet"], "sbl_Latn": ["data/sbl_Latn/train/000_00000.parquet"], "sbs_Latn": ["data/sbs_Latn/train/000_00000.parquet"], "sby_Latn": ["data/sby_Latn/train/000_00000.parquet"], "sck_Deva": ["data/sck_Deva/train/000_00000.parquet"], "scn_Latn": ["data/scn_Latn/train/000_00000.parquet"], "sco_Latn": ["data/sco_Latn/train/000_00000.parquet"], "sda_Latn": ["data/sda_Latn/train/000_00000.parquet"], "sdc_Latn": ["data/sdc_Latn/train/000_00000.parquet"], "sdh_Arab": ["data/sdh_Arab/train/000_00000.parquet"], "sdo_Latn": ["data/sdo_Latn/train/000_00000.parquet"], "sdq_Latn": ["data/sdq_Latn/train/000_00000.parquet"], "seh_Latn": ["data/seh_Latn/train/000_00000.parquet"], "ses_Latn": ["data/ses_Latn/train/000_00000.parquet"], "sey_Latn": ["data/sey_Latn/train/000_00000.parquet"], "sfw_Latn": ["data/sfw_Latn/train/000_00000.parquet"], "sgb_Latn": ["data/sgb_Latn/train/000_00000.parquet"], "sgc_Latn": ["data/sgc_Latn/train/000_00000.parquet"], "sgh_Cyrl": ["data/sgh_Cyrl/train/000_00000.parquet"], "sgs_Latn": ["data/sgs_Latn/train/000_00000.parquet"], "sgw_Ethi": ["data/sgw_Ethi/train/000_00000.parquet"], "sgz_Latn": ["data/sgz_Latn/train/000_00000.parquet"], "shi_Latn": ["data/shi_Latn/train/000_00000.parquet"], "shk_Latn": ["data/shk_Latn/train/000_00000.parquet"], "shn_Mymr": ["data/shn_Mymr/train/000_00000.parquet"], "shp_Latn": ["data/shp_Latn/train/000_00000.parquet"], "shu_Arab": ["data/shu_Arab/train/000_00000.parquet"], "sid_Latn": ["data/sid_Latn/train/000_00000.parquet"], "sig_Latn": ["data/sig_Latn/train/000_00000.parquet"], "sil_Latn": ["data/sil_Latn/train/000_00000.parquet"], "sim_Latn": ["data/sim_Latn/train/000_00000.parquet"], "sin_Sinh": ["data/sin_Sinh/train/000_00000.parquet"], "sja_Latn": ["data/sja_Latn/train/000_00000.parquet"], "sjo_Mong": ["data/sjo_Mong/train/000_00000.parquet"], "sju_Latn": ["data/sju_Latn/train/000_00000.parquet"], "skg_Latn": ["data/skg_Latn/train/000_00000.parquet"], "skr_Arab": ["data/skr_Arab/train/000_00000.parquet"], "sld_Latn": ["data/sld_Latn/train/000_00000.parquet"], "slk_Latn": ["data/slk_Latn/train/000_00000.parquet", "data/slk_Latn/train/000_00001.parquet", "data/slk_Latn/train/001_00000.parquet"], "sll_Latn": ["data/sll_Latn/train/000_00000.parquet"], "slv_Latn": ["data/slv_Latn/train/000_00000.parquet", "data/slv_Latn/train/001_00000.parquet", "data/slv_Latn/train/002_00000.parquet"], "sma_Latn": ["data/sma_Latn/train/000_00000.parquet"], "sme_Latn": ["data/sme_Latn/train/000_00000.parquet"], "smj_Latn": ["data/smj_Latn/train/000_00000.parquet"], "smk_Latn": ["data/smk_Latn/train/000_00000.parquet"], "sml_Latn": ["data/sml_Latn/train/000_00000.parquet"], "smn_Latn": ["data/smn_Latn/train/000_00000.parquet"], "smo_Latn": ["data/smo_Latn/train/000_00000.parquet"], "sms_Latn": ["data/sms_Latn/train/000_00000.parquet"], "smt_Latn": ["data/smt_Latn/train/000_00000.parquet"], "sna_Latn": ["data/sna_Latn/train/000_00000.parquet"], "snc_Latn": ["data/snc_Latn/train/000_00000.parquet"], "snd_Arab": ["data/snd_Arab/train/000_00000.parquet"], "snd_Deva": ["data/snd_Deva/train/000_00000.parquet"], "snd_Latn": ["data/snd_Latn/train/000_00000.parquet"], "snf_Latn": ["data/snf_Latn/train/000_00000.parquet"], "snn_Latn": ["data/snn_Latn/train/000_00000.parquet"], "snp_Latn": ["data/snp_Latn/train/000_00000.parquet"], "snw_Latn": ["data/snw_Latn/train/000_00000.parquet"], "sny_Latn": ["data/sny_Latn/train/000_00000.parquet"], "soe_Latn": ["data/soe_Latn/train/000_00000.parquet"], "som_Latn": ["data/som_Latn/train/000_00000.parquet"], "sop_Latn": ["data/sop_Latn/train/000_00000.parquet"], "soq_Latn": ["data/soq_Latn/train/000_00000.parquet"], "sot_Latn": ["data/sot_Latn/train/000_00000.parquet"], "soy_Latn": ["data/soy_Latn/train/000_00000.parquet"], "spa_Latn": ["data/spa_Latn/train/000_00000.parquet", "data/spa_Latn/train/000_00001.parquet", "data/spa_Latn/train/000_00002.parquet"], "spl_Latn": ["data/spl_Latn/train/000_00000.parquet"], "spm_Latn": ["data/spm_Latn/train/000_00000.parquet"], "spp_Latn": ["data/spp_Latn/train/000_00000.parquet"], "sps_Latn": ["data/sps_Latn/train/000_00000.parquet"], "spy_Latn": ["data/spy_Latn/train/000_00000.parquet"], "srd_Latn": ["data/srd_Latn/train/000_00000.parquet"], "sri_Latn": ["data/sri_Latn/train/000_00000.parquet"], "srm_Latn": ["data/srm_Latn/train/000_00000.parquet"], "srn_Latn": ["data/srn_Latn/train/000_00000.parquet"], "srp_Cyrl": ["data/srp_Cyrl/train/000_00000.parquet", "data/srp_Cyrl/train/001_00000.parquet"], "srp_Latn": ["data/srp_Latn/train/000_00000.parquet"], "srq_Latn": ["data/srq_Latn/train/000_00000.parquet"], "srr_Latn": ["data/srr_Latn/train/000_00000.parquet"], "ssd_Latn": ["data/ssd_Latn/train/000_00000.parquet"], "ssg_Latn": ["data/ssg_Latn/train/000_00000.parquet"], "ssw_Latn": ["data/ssw_Latn/train/000_00000.parquet"], "ssx_Latn": ["data/ssx_Latn/train/000_00000.parquet"], "stn_Latn": ["data/stn_Latn/train/000_00000.parquet"], "stp_Latn": ["data/stp_Latn/train/000_00000.parquet"], "stq_Latn": ["data/stq_Latn/train/000_00000.parquet"], "sua_Latn": ["data/sua_Latn/train/000_00000.parquet"], "suc_Latn": ["data/suc_Latn/train/000_00000.parquet"], "sue_Latn": ["data/sue_Latn/train/000_00000.parquet"], "suk_Latn": ["data/suk_Latn/train/000_00000.parquet"], "sun_Latn": ["data/sun_Latn/train/000_00000.parquet"], "sur_Latn": ["data/sur_Latn/train/000_00000.parquet"], "sus_Arab": ["data/sus_Arab/train/000_00000.parquet"], "sus_Latn": ["data/sus_Latn/train/000_00000.parquet"], "suz_Deva": ["data/suz_Deva/train/000_00000.parquet"], "swb_Latn": ["data/swb_Latn/train/000_00000.parquet"], "swc_Latn": ["data/swc_Latn/train/000_00000.parquet"], "swe_Latn": ["data/swe_Latn/train/000_00000.parquet", "data/swe_Latn/train/000_00001.parquet", "data/swe_Latn/train/000_00002.parquet"], "swg_Latn": ["data/swg_Latn/train/000_00000.parquet"], "swh_Latn": ["data/swh_Latn/train/000_00000.parquet"], "swk_Latn": ["data/swk_Latn/train/000_00000.parquet"], "swp_Latn": ["data/swp_Latn/train/000_00000.parquet"], "sxb_Latn": ["data/sxb_Latn/train/000_00000.parquet"], "sxn_Latn": ["data/sxn_Latn/train/000_00000.parquet"], "syb_Latn": ["data/syb_Latn/train/000_00000.parquet"], "syc_Syrc": ["data/syc_Syrc/train/000_00000.parquet"], "syl_Beng": ["data/syl_Beng/train/000_00000.parquet"], "syl_Latn": ["data/syl_Latn/train/000_00000.parquet"], "szl_Latn": ["data/szl_Latn/train/000_00000.parquet"], "szy_Latn": ["data/szy_Latn/train/000_00000.parquet"], "tab_Cyrl": ["data/tab_Cyrl/train/000_00000.parquet"], "tac_Latn": ["data/tac_Latn/train/000_00000.parquet"], "tah_Latn": ["data/tah_Latn/train/000_00000.parquet"], "taj_Deva": ["data/taj_Deva/train/000_00000.parquet"], "tam_Latn": ["data/tam_Latn/train/000_00000.parquet"], "tam_Taml": ["data/tam_Taml/train/000_00000.parquet", "data/tam_Taml/train/001_00000.parquet"], "tap_Latn": ["data/tap_Latn/train/000_00000.parquet"], "taq_Latn": ["data/taq_Latn/train/000_00000.parquet"], "taq_Tfng": ["data/taq_Tfng/train/000_00000.parquet"], "tar_Latn": ["data/tar_Latn/train/000_00000.parquet"], "tat_Cyrl": ["data/tat_Cyrl/train/000_00000.parquet"], "tat_Latn": ["data/tat_Latn/train/000_00000.parquet"], "tav_Latn": ["data/tav_Latn/train/000_00000.parquet"], "taw_Latn": ["data/taw_Latn/train/000_00000.parquet"], "tay_Latn": ["data/tay_Latn/train/000_00000.parquet"], "tbc_Latn": ["data/tbc_Latn/train/000_00000.parquet"], "tbg_Latn": ["data/tbg_Latn/train/000_00000.parquet"], "tbk_Latn": ["data/tbk_Latn/train/000_00000.parquet"], "tbl_Latn": ["data/tbl_Latn/train/000_00000.parquet"], "tbo_Latn": ["data/tbo_Latn/train/000_00000.parquet"], "tbw_Latn": ["data/tbw_Latn/train/000_00000.parquet"], "tby_Latn": ["data/tby_Latn/train/000_00000.parquet"], "tbz_Latn": ["data/tbz_Latn/train/000_00000.parquet"], "tca_Latn": ["data/tca_Latn/train/000_00000.parquet"], "tcc_Latn": ["data/tcc_Latn/train/000_00000.parquet"], "tcf_Latn": ["data/tcf_Latn/train/000_00000.parquet"], "tcs_Latn": ["data/tcs_Latn/train/000_00000.parquet"], "tcy_Knda": ["data/tcy_Knda/train/000_00000.parquet"], "tcz_Latn": ["data/tcz_Latn/train/000_00000.parquet"], "ted_Latn": ["data/ted_Latn/train/000_00000.parquet"], "tee_Latn": ["data/tee_Latn/train/000_00000.parquet"], "tel_Latn": ["data/tel_Latn/train/000_00000.parquet"], "tel_Telu": ["data/tel_Telu/train/000_00000.parquet"], "tem_Latn": ["data/tem_Latn/train/000_00000.parquet"], "teo_Latn": ["data/teo_Latn/train/000_00000.parquet"], "ter_Latn": ["data/ter_Latn/train/000_00000.parquet"], "tet_Latn": ["data/tet_Latn/train/000_00000.parquet"], "tew_Latn": ["data/tew_Latn/train/000_00000.parquet"], "tfr_Latn": ["data/tfr_Latn/train/000_00000.parquet"], "tgk_Cyrl": ["data/tgk_Cyrl/train/000_00000.parquet"], "tgo_Latn": ["data/tgo_Latn/train/000_00000.parquet"], "tgp_Latn": ["data/tgp_Latn/train/000_00000.parquet"], "tha_Thai": ["data/tha_Thai/train/000_00000.parquet", "data/tha_Thai/train/000_00001.parquet", "data/tha_Thai/train/000_00002.parquet"], "thk_Latn": ["data/thk_Latn/train/000_00000.parquet"], "thl_Deva": ["data/thl_Deva/train/000_00000.parquet"], "tif_Latn": ["data/tif_Latn/train/000_00000.parquet"], "tig_Ethi": ["data/tig_Ethi/train/000_00000.parquet"], "tih_Latn": ["data/tih_Latn/train/000_00000.parquet"], "tik_Latn": ["data/tik_Latn/train/000_00000.parquet"], "tim_Latn": ["data/tim_Latn/train/000_00000.parquet"], "tir_Ethi": ["data/tir_Ethi/train/000_00000.parquet"], "tiv_Latn": ["data/tiv_Latn/train/000_00000.parquet"], "tiy_Latn": ["data/tiy_Latn/train/000_00000.parquet"], "tke_Latn": ["data/tke_Latn/train/000_00000.parquet"], "tkl_Latn": ["data/tkl_Latn/train/000_00000.parquet"], "tkr_Cyrl": ["data/tkr_Cyrl/train/000_00000.parquet"], "tku_Latn": ["data/tku_Latn/train/000_00000.parquet"], "tlb_Latn": ["data/tlb_Latn/train/000_00000.parquet"], "tlf_Latn": ["data/tlf_Latn/train/000_00000.parquet"], "tlh_Latn": ["data/tlh_Latn/train/000_00000.parquet"], "tlj_Latn": ["data/tlj_Latn/train/000_00000.parquet"], "tll_Latn": ["data/tll_Latn/train/000_00000.parquet"], "tly_Latn": ["data/tly_Latn/train/000_00000.parquet"], "tmc_Latn": ["data/tmc_Latn/train/000_00000.parquet"], "tmd_Latn": ["data/tmd_Latn/train/000_00000.parquet"], "tna_Latn": ["data/tna_Latn/train/000_00000.parquet"], "tnc_Latn": ["data/tnc_Latn/train/000_00000.parquet"], "tnk_Latn": ["data/tnk_Latn/train/000_00000.parquet"], "tnn_Latn": ["data/tnn_Latn/train/000_00000.parquet"], "tnp_Latn": ["data/tnp_Latn/train/000_00000.parquet"], "tnr_Latn": ["data/tnr_Latn/train/000_00000.parquet"], "tob_Latn": ["data/tob_Latn/train/000_00000.parquet"], "toc_Latn": ["data/toc_Latn/train/000_00000.parquet"], "tod_Latn": ["data/tod_Latn/train/000_00000.parquet"], "tog_Latn": ["data/tog_Latn/train/000_00000.parquet"], "toh_Latn": ["data/toh_Latn/train/000_00000.parquet"], "toi_Latn": ["data/toi_Latn/train/000_00000.parquet"], "toj_Latn": ["data/toj_Latn/train/000_00000.parquet"], "tok_Latn": ["data/tok_Latn/train/000_00000.parquet"], "ton_Latn": ["data/ton_Latn/train/000_00000.parquet"], "too_Latn": ["data/too_Latn/train/000_00000.parquet"], "top_Latn": ["data/top_Latn/train/000_00000.parquet"], "tos_Latn": ["data/tos_Latn/train/000_00000.parquet"], "tpa_Latn": ["data/tpa_Latn/train/000_00000.parquet"], "tpi_Latn": ["data/tpi_Latn/train/000_00000.parquet"], "tpm_Latn": ["data/tpm_Latn/train/000_00000.parquet"], "tpp_Latn": ["data/tpp_Latn/train/000_00000.parquet"], "tpt_Latn": ["data/tpt_Latn/train/000_00000.parquet"], "tpw_Latn": ["data/tpw_Latn/train/000_00000.parquet"], "tpz_Latn": ["data/tpz_Latn/train/000_00000.parquet"], "tqo_Latn": ["data/tqo_Latn/train/000_00000.parquet"], "trc_Latn": ["data/trc_Latn/train/000_00000.parquet"], "trn_Latn": ["data/trn_Latn/train/000_00000.parquet"], "tro_Latn": ["data/tro_Latn/train/000_00000.parquet"], "trp_Latn": ["data/trp_Latn/train/000_00000.parquet"], "trq_Latn": ["data/trq_Latn/train/000_00000.parquet"], "trs_Latn": ["data/trs_Latn/train/000_00000.parquet"], "trv_Latn": ["data/trv_Latn/train/000_00000.parquet"], "tsc_Latn": ["data/tsc_Latn/train/000_00000.parquet"], "tsg_Latn": ["data/tsg_Latn/train/000_00000.parquet"], "tsn_Latn": ["data/tsn_Latn/train/000_00000.parquet"], "tso_Latn": ["data/tso_Latn/train/000_00000.parquet"], "tsw_Latn": ["data/tsw_Latn/train/000_00000.parquet"], "tsz_Latn": ["data/tsz_Latn/train/000_00000.parquet"], "ttc_Latn": ["data/ttc_Latn/train/000_00000.parquet"], "tte_Latn": ["data/tte_Latn/train/000_00000.parquet"], "ttj_Latn": ["data/ttj_Latn/train/000_00000.parquet"], "ttq_Latn": ["data/ttq_Latn/train/000_00000.parquet"], "ttq_Tfng": ["data/ttq_Tfng/train/000_00000.parquet"], "tuc_Latn": ["data/tuc_Latn/train/000_00000.parquet"], "tue_Latn": ["data/tue_Latn/train/000_00000.parquet"], "tuf_Latn": ["data/tuf_Latn/train/000_00000.parquet"], "tui_Latn": ["data/tui_Latn/train/000_00000.parquet"], "tuk_Arab": ["data/tuk_Arab/train/000_00000.parquet"], "tuk_Cyrl": ["data/tuk_Cyrl/train/000_00000.parquet"], "tuk_Latn": ["data/tuk_Latn/train/000_00000.parquet"], "tul_Latn": ["data/tul_Latn/train/000_00000.parquet"], "tum_Latn": ["data/tum_Latn/train/000_00000.parquet"], "tuo_Latn": ["data/tuo_Latn/train/000_00000.parquet"], "tur_Latn": ["data/tur_Latn/train/000_00000.parquet", "data/tur_Latn/train/000_00001.parquet", "data/tur_Latn/train/000_00002.parquet"], "tuv_Latn": ["data/tuv_Latn/train/000_00000.parquet"], "tvk_Latn": ["data/tvk_Latn/train/000_00000.parquet"], "tvl_Latn": ["data/tvl_Latn/train/000_00000.parquet"], "twi_Latn": ["data/twi_Latn/train/000_00000.parquet"], "twu_Latn": ["data/twu_Latn/train/000_00000.parquet"], "twx_Latn": ["data/twx_Latn/train/000_00000.parquet"], "txq_Latn": ["data/txq_Latn/train/000_00000.parquet"], "txu_Latn": ["data/txu_Latn/train/000_00000.parquet"], "tyv_Cyrl": ["data/tyv_Cyrl/train/000_00000.parquet"], "tzh_Latn": ["data/tzh_Latn/train/000_00000.parquet"], "tzj_Latn": ["data/tzj_Latn/train/000_00000.parquet"], "tzl_Latn": ["data/tzl_Latn/train/000_00000.parquet"], "tzm_Tfng": ["data/tzm_Tfng/train/000_00000.parquet"], "tzo_Latn": ["data/tzo_Latn/train/000_00000.parquet"], "ubr_Latn": ["data/ubr_Latn/train/000_00000.parquet"], "ubu_Latn": ["data/ubu_Latn/train/000_00000.parquet"], "udm_Cyrl": ["data/udm_Cyrl/train/000_00000.parquet"], "udu_Latn": ["data/udu_Latn/train/000_00000.parquet"], "uig_Arab": ["data/uig_Arab/train/000_00000.parquet"], "uig_Cyrl": ["data/uig_Cyrl/train/000_00000.parquet"], "uig_Latn": ["data/uig_Latn/train/000_00000.parquet"], "ukr_Cyrl": ["data/ukr_Cyrl/train/000_00000.parquet", "data/ukr_Cyrl/train/000_00001.parquet", "data/ukr_Cyrl/train/000_00002.parquet"], "umb_Latn": ["data/umb_Latn/train/000_00000.parquet"], "und_Armn": ["data/und_Armn/train/000_00000.parquet"], "und_Bali": ["data/und_Bali/train/000_00000.parquet"], "und_Bamu": ["data/und_Bamu/train/000_00000.parquet"], "und_Beng": ["data/und_Beng/train/000_00000.parquet"], "und_Bopo": ["data/und_Bopo/train/000_00000.parquet"], "und_Brai": ["data/und_Brai/train/000_00000.parquet"], "und_Cans": ["data/und_Cans/train/000_00000.parquet"], "und_Cher": ["data/und_Cher/train/000_00000.parquet"], "und_Cyrl": ["data/und_Cyrl/train/000_00000.parquet"], "und_Deva": ["data/und_Deva/train/000_00000.parquet"], "und_Egyp": ["data/und_Egyp/train/000_00000.parquet"], "und_Ethi": ["data/und_Ethi/train/000_00000.parquet"], "und_Geor": ["data/und_Geor/train/000_00000.parquet"], "und_Goth": ["data/und_Goth/train/000_00000.parquet"], "und_Grek": ["data/und_Grek/train/000_00000.parquet"], "und_Hebr": ["data/und_Hebr/train/000_00000.parquet"], "und_Hira": ["data/und_Hira/train/000_00000.parquet"], "und_Hluw": ["data/und_Hluw/train/000_00000.parquet"], "und_Hung": ["data/und_Hung/train/000_00000.parquet"], "und_Kana": ["data/und_Kana/train/000_00000.parquet"], "und_Khmr": ["data/und_Khmr/train/000_00000.parquet"], "und_Knda": ["data/und_Knda/train/000_00000.parquet"], "und_Lana": ["data/und_Lana/train/000_00000.parquet"], "und_Laoo": ["data/und_Laoo/train/000_00000.parquet"], "und_Lina": ["data/und_Lina/train/000_00000.parquet"], "und_Mlym": ["data/und_Mlym/train/000_00000.parquet"], "und_Mong": ["data/und_Mong/train/000_00000.parquet"], "und_Mymr": ["data/und_Mymr/train/000_00000.parquet"], "und_Newa": ["data/und_Newa/train/000_00000.parquet"], "und_Orya": ["data/und_Orya/train/000_00000.parquet"], "und_Sgnw": ["data/und_Sgnw/train/000_00000.parquet"], "und_Shaw": ["data/und_Shaw/train/000_00000.parquet"], "und_Sylo": ["data/und_Sylo/train/000_00000.parquet"], "und_Syrc": ["data/und_Syrc/train/000_00000.parquet"], "und_Taml": ["data/und_Taml/train/000_00000.parquet"], "und_Tang": ["data/und_Tang/train/000_00000.parquet"], "und_Telu": ["data/und_Telu/train/000_00000.parquet"], "und_Thaa": ["data/und_Thaa/train/000_00000.parquet"], "und_Thai": ["data/und_Thai/train/000_00000.parquet"], "und_Tibt": ["data/und_Tibt/train/000_00000.parquet"], "und_Vaii": ["data/und_Vaii/train/000_00000.parquet"], "und_Xsux": ["data/und_Xsux/train/000_00000.parquet"], "und_Yiii": ["data/und_Yiii/train/000_00000.parquet"], "upv_Latn": ["data/upv_Latn/train/000_00000.parquet"], "ura_Latn": ["data/ura_Latn/train/000_00000.parquet"], "urb_Latn": ["data/urb_Latn/train/000_00000.parquet"], "urd_Arab": ["data/urd_Arab/train/000_00000.parquet", "data/urd_Arab/train/001_00000.parquet"], "urd_Latn": ["data/urd_Latn/train/000_00000.parquet"], "urh_Latn": ["data/urh_Latn/train/000_00000.parquet"], "uri_Latn": ["data/uri_Latn/train/000_00000.parquet"], "urk_Thai": ["data/urk_Thai/train/000_00000.parquet"], "urt_Latn": ["data/urt_Latn/train/000_00000.parquet"], "urw_Latn": ["data/urw_Latn/train/000_00000.parquet"], "ury_Latn": ["data/ury_Latn/train/000_00000.parquet"], "usa_Latn": ["data/usa_Latn/train/000_00000.parquet"], "usp_Latn": ["data/usp_Latn/train/000_00000.parquet"], "uth_Latn": ["data/uth_Latn/train/000_00000.parquet"], "uvh_Latn": ["data/uvh_Latn/train/000_00000.parquet"], "uvl_Latn": ["data/uvl_Latn/train/000_00000.parquet"], "uzn_Cyrl": ["data/uzn_Cyrl/train/000_00000.parquet"], "uzn_Latn": ["data/uzn_Latn/train/000_00000.parquet"], "uzs_Arab": ["data/uzs_Arab/train/000_00000.parquet"], "vag_Latn": ["data/vag_Latn/train/000_00000.parquet"], "vap_Latn": ["data/vap_Latn/train/000_00000.parquet"], "var_Latn": ["data/var_Latn/train/000_00000.parquet"], "vec_Latn": ["data/vec_Latn/train/000_00000.parquet"], "ven_Latn": ["data/ven_Latn/train/000_00000.parquet"], "vep_Latn": ["data/vep_Latn/train/000_00000.parquet"], "vid_Latn": ["data/vid_Latn/train/000_00000.parquet"], "vie_Latn": ["data/vie_Latn/train/000_00000.parquet", "data/vie_Latn/train/000_00001.parquet", "data/vie_Latn/train/000_00002.parquet"], "viv_Latn": ["data/viv_Latn/train/000_00000.parquet"], "vls_Latn": ["data/vls_Latn/train/000_00000.parquet"], "vmk_Latn": ["data/vmk_Latn/train/000_00000.parquet"], "vmw_Latn": ["data/vmw_Latn/train/000_00000.parquet"], "vmy_Latn": ["data/vmy_Latn/train/000_00000.parquet"], "vol_Latn": ["data/vol_Latn/train/000_00000.parquet"], "vot_Latn": ["data/vot_Latn/train/000_00000.parquet"], "vro_Latn": ["data/vro_Latn/train/000_00000.parquet"], "vun_Latn": ["data/vun_Latn/train/000_00000.parquet"], "vut_Latn": ["data/vut_Latn/train/000_00000.parquet"], "waj_Latn": ["data/waj_Latn/train/000_00000.parquet"], "wal_Latn": ["data/wal_Latn/train/000_00000.parquet"], "wap_Latn": ["data/wap_Latn/train/000_00000.parquet"], "war_Latn": ["data/war_Latn/train/000_00000.parquet"], "wat_Latn": ["data/wat_Latn/train/000_00000.parquet"], "way_Latn": ["data/way_Latn/train/000_00000.parquet"], "wba_Latn": ["data/wba_Latn/train/000_00000.parquet"], "wbm_Latn": ["data/wbm_Latn/train/000_00000.parquet"], "wbp_Latn": ["data/wbp_Latn/train/000_00000.parquet"], "wed_Latn": ["data/wed_Latn/train/000_00000.parquet"], "wer_Latn": ["data/wer_Latn/train/000_00000.parquet"], "wes_Latn": ["data/wes_Latn/train/000_00000.parquet"], "wew_Latn": ["data/wew_Latn/train/000_00000.parquet"], "whg_Latn": ["data/whg_Latn/train/000_00000.parquet"], "whk_Latn": ["data/whk_Latn/train/000_00000.parquet"], "wib_Latn": ["data/wib_Latn/train/000_00000.parquet"], "wim_Latn": ["data/wim_Latn/train/000_00000.parquet"], "wiu_Latn": ["data/wiu_Latn/train/000_00000.parquet"], "wln_Latn": ["data/wln_Latn/train/000_00000.parquet"], "wls_Latn": ["data/wls_Latn/train/000_00000.parquet"], "wlv_Latn": ["data/wlv_Latn/train/000_00000.parquet"], "wlx_Latn": ["data/wlx_Latn/train/000_00000.parquet"], "wmt_Latn": ["data/wmt_Latn/train/000_00000.parquet"], "wmw_Latn": ["data/wmw_Latn/train/000_00000.parquet"], "wnc_Latn": ["data/wnc_Latn/train/000_00000.parquet"], "wnu_Latn": ["data/wnu_Latn/train/000_00000.parquet"], "wob_Latn": ["data/wob_Latn/train/000_00000.parquet"], "wol_Latn": ["data/wol_Latn/train/000_00000.parquet"], "wos_Latn": ["data/wos_Latn/train/000_00000.parquet"], "wrk_Latn": ["data/wrk_Latn/train/000_00000.parquet"], "wrs_Latn": ["data/wrs_Latn/train/000_00000.parquet"], "wsg_Telu": ["data/wsg_Telu/train/000_00000.parquet"], "wsk_Latn": ["data/wsk_Latn/train/000_00000.parquet"], "wuu_Hani": ["data/wuu_Hani/train/000_00000.parquet"], "wuv_Latn": ["data/wuv_Latn/train/000_00000.parquet"], "wwa_Latn": ["data/wwa_Latn/train/000_00000.parquet"], "xal_Cyrl": ["data/xal_Cyrl/train/000_00000.parquet"], "xav_Latn": ["data/xav_Latn/train/000_00000.parquet"], "xbi_Latn": ["data/xbi_Latn/train/000_00000.parquet"], "xbr_Latn": ["data/xbr_Latn/train/000_00000.parquet"], "xed_Latn": ["data/xed_Latn/train/000_00000.parquet"], "xho_Latn": ["data/xho_Latn/train/000_00000.parquet"], "xla_Latn": ["data/xla_Latn/train/000_00000.parquet"], "xmf_Geor": ["data/xmf_Geor/train/000_00000.parquet"], "xmm_Latn": ["data/xmm_Latn/train/000_00000.parquet"], "xmv_Latn": ["data/xmv_Latn/train/000_00000.parquet"], "xnn_Latn": ["data/xnn_Latn/train/000_00000.parquet"], "xog_Latn": ["data/xog_Latn/train/000_00000.parquet"], "xon_Latn": ["data/xon_Latn/train/000_00000.parquet"], "xrb_Latn": ["data/xrb_Latn/train/000_00000.parquet"], "xsb_Latn": ["data/xsb_Latn/train/000_00000.parquet"], "xsi_Latn": ["data/xsi_Latn/train/000_00000.parquet"], "xsm_Latn": ["data/xsm_Latn/train/000_00000.parquet"], "xsr_Deva": ["data/xsr_Deva/train/000_00000.parquet"], "xsu_Latn": ["data/xsu_Latn/train/000_00000.parquet"], "xtd_Latn": ["data/xtd_Latn/train/000_00000.parquet"], "xtm_Latn": ["data/xtm_Latn/train/000_00000.parquet"], "xtn_Latn": ["data/xtn_Latn/train/000_00000.parquet"], "xuo_Latn": ["data/xuo_Latn/train/000_00000.parquet"], "yaa_Latn": ["data/yaa_Latn/train/000_00000.parquet"], "yad_Latn": ["data/yad_Latn/train/000_00000.parquet"], "yal_Latn": ["data/yal_Latn/train/000_00000.parquet"], "yam_Latn": ["data/yam_Latn/train/000_00000.parquet"], "yan_Latn": ["data/yan_Latn/train/000_00000.parquet"], "yao_Latn": ["data/yao_Latn/train/000_00000.parquet"], "yap_Latn": ["data/yap_Latn/train/000_00000.parquet"], "yaq_Latn": ["data/yaq_Latn/train/000_00000.parquet"], "yat_Latn": ["data/yat_Latn/train/000_00000.parquet"], "yaz_Latn": ["data/yaz_Latn/train/000_00000.parquet"], "ybb_Latn": ["data/ybb_Latn/train/000_00000.parquet"], "yby_Latn": ["data/yby_Latn/train/000_00000.parquet"], "ycn_Latn": ["data/ycn_Latn/train/000_00000.parquet"], "ydd_Hebr": ["data/ydd_Hebr/train/000_00000.parquet"], "yim_Latn": ["data/yim_Latn/train/000_00000.parquet"], "yka_Latn": ["data/yka_Latn/train/000_00000.parquet"], "yle_Latn": ["data/yle_Latn/train/000_00000.parquet"], "yli_Latn": ["data/yli_Latn/train/000_00000.parquet"], "yml_Latn": ["data/yml_Latn/train/000_00000.parquet"], "yom_Latn": ["data/yom_Latn/train/000_00000.parquet"], "yon_Latn": ["data/yon_Latn/train/000_00000.parquet"], "yor_Latn": ["data/yor_Latn/train/000_00000.parquet"], "yrb_Latn": ["data/yrb_Latn/train/000_00000.parquet"], "yre_Latn": ["data/yre_Latn/train/000_00000.parquet"], "yrk_Cyrl": ["data/yrk_Cyrl/train/000_00000.parquet"], "yrl_Latn": ["data/yrl_Latn/train/000_00000.parquet"], "yss_Latn": ["data/yss_Latn/train/000_00000.parquet"], "yua_Latn": ["data/yua_Latn/train/000_00000.parquet"], "yue_Hani": ["data/yue_Hani/train/000_00000.parquet"], "yuj_Latn": ["data/yuj_Latn/train/000_00000.parquet"], "yup_Latn": ["data/yup_Latn/train/000_00000.parquet"], "yut_Latn": ["data/yut_Latn/train/000_00000.parquet"], "yuw_Latn": ["data/yuw_Latn/train/000_00000.parquet"], "yuz_Latn": ["data/yuz_Latn/train/000_00000.parquet"], "yva_Latn": ["data/yva_Latn/train/000_00000.parquet"], "zaa_Latn": ["data/zaa_Latn/train/000_00000.parquet"], "zab_Latn": ["data/zab_Latn/train/000_00000.parquet"], "zac_Latn": ["data/zac_Latn/train/000_00000.parquet"], "zad_Latn": ["data/zad_Latn/train/000_00000.parquet"], "zae_Latn": ["data/zae_Latn/train/000_00000.parquet"], "zai_Latn": ["data/zai_Latn/train/000_00000.parquet"], "zam_Latn": ["data/zam_Latn/train/000_00000.parquet"], "zao_Latn": ["data/zao_Latn/train/000_00000.parquet"], "zar_Latn": ["data/zar_Latn/train/000_00000.parquet"], "zas_Latn": ["data/zas_Latn/train/000_00000.parquet"], "zat_Latn": ["data/zat_Latn/train/000_00000.parquet"], "zav_Latn": ["data/zav_Latn/train/000_00000.parquet"], "zaw_Latn": ["data/zaw_Latn/train/000_00000.parquet"], "zca_Latn": ["data/zca_Latn/train/000_00000.parquet"], "zdj_Latn": ["data/zdj_Latn/train/000_00000.parquet"], "zea_Latn": ["data/zea_Latn/train/000_00000.parquet"], "zgh_Tfng": ["data/zgh_Tfng/train/000_00000.parquet"], "zia_Latn": ["data/zia_Latn/train/000_00000.parquet"], "ziw_Latn": ["data/ziw_Latn/train/000_00000.parquet"], "zne_Latn": ["data/zne_Latn/train/000_00000.parquet"], "zom_Latn": ["data/zom_Latn/train/000_00000.parquet"], "zos_Latn": ["data/zos_Latn/train/000_00000.parquet"], "zpa_Latn": ["data/zpa_Latn/train/000_00000.parquet"], "zpc_Latn": ["data/zpc_Latn/train/000_00000.parquet"], "zpg_Latn": ["data/zpg_Latn/train/000_00000.parquet"], "zpi_Latn": ["data/zpi_Latn/train/000_00000.parquet"], "zpj_Latn": ["data/zpj_Latn/train/000_00000.parquet"], "zpl_Latn": ["data/zpl_Latn/train/000_00000.parquet"], "zpm_Latn": ["data/zpm_Latn/train/000_00000.parquet"], "zpo_Latn": ["data/zpo_Latn/train/000_00000.parquet"], "zpq_Latn": ["data/zpq_Latn/train/000_00000.parquet"], "zpt_Latn": ["data/zpt_Latn/train/000_00000.parquet"], "zpu_Latn": ["data/zpu_Latn/train/000_00000.parquet"], "zpv_Latn": ["data/zpv_Latn/train/000_00000.parquet"], "zpz_Latn": ["data/zpz_Latn/train/000_00000.parquet"], "zsm_Arab": ["data/zsm_Arab/train/000_00000.parquet"], "zsm_Latn": ["data/zsm_Latn/train/000_00000.parquet", "data/zsm_Latn/train/001_00000.parquet", "data/zsm_Latn/train/002_00000.parquet"], "zsr_Latn": ["data/zsr_Latn/train/000_00000.parquet"], "ztq_Latn": ["data/ztq_Latn/train/000_00000.parquet"], "zty_Latn": ["data/zty_Latn/train/000_00000.parquet"], "zul_Latn": ["data/zul_Latn/train/000_00000.parquet"], "zyb_Latn": ["data/zyb_Latn/train/000_00000.parquet"], "zyp_Latn": ["data/zyp_Latn/train/000_00000.parquet"]}, "fineweb_eng": ["sample/10BT/000_00000.parquet", "sample/10BT/001_00000.parquet"]}