Commit
•
ff8891d
1
Parent(s):
8728195
add tokenizer files
Browse files- added_tokens.json +209 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +259 -0
- tokenizer_config.json +1914 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 282723,
|
| 3 |
+
"ace_Arab": 282724,
|
| 4 |
+
"ace_Latn": 282725,
|
| 5 |
+
"acm_Arab": 282726,
|
| 6 |
+
"acq_Arab": 282727,
|
| 7 |
+
"aeb_Arab": 282728,
|
| 8 |
+
"afr_Latn": 282729,
|
| 9 |
+
"ajp_Arab": 282730,
|
| 10 |
+
"aka_Latn": 282731,
|
| 11 |
+
"als_Latn": 282732,
|
| 12 |
+
"amh_Ethi": 282733,
|
| 13 |
+
"apc_Arab": 282734,
|
| 14 |
+
"arb_Arab": 282735,
|
| 15 |
+
"ars_Arab": 282736,
|
| 16 |
+
"ary_Arab": 282737,
|
| 17 |
+
"arz_Arab": 282738,
|
| 18 |
+
"asm_Beng": 282739,
|
| 19 |
+
"ast_Latn": 282740,
|
| 20 |
+
"awa_Deva": 282741,
|
| 21 |
+
"ayr_Latn": 282742,
|
| 22 |
+
"azb_Arab": 282743,
|
| 23 |
+
"azj_Latn": 282744,
|
| 24 |
+
"bak_Cyrl": 282745,
|
| 25 |
+
"bam_Latn": 282746,
|
| 26 |
+
"ban_Latn": 282747,
|
| 27 |
+
"bel_Cyrl": 282748,
|
| 28 |
+
"bem_Latn": 282749,
|
| 29 |
+
"ben_Beng": 282750,
|
| 30 |
+
"bho_Deva": 282751,
|
| 31 |
+
"bjn_Arab": 282752,
|
| 32 |
+
"bjn_Latn": 282753,
|
| 33 |
+
"bod_Tibt": 282754,
|
| 34 |
+
"bos_Latn": 282755,
|
| 35 |
+
"bug_Latn": 282756,
|
| 36 |
+
"bul_Cyrl": 282757,
|
| 37 |
+
"bxr_Cyrl": 282758,
|
| 38 |
+
"cat_Latn": 282759,
|
| 39 |
+
"ceb_Latn": 282760,
|
| 40 |
+
"ces_Latn": 282761,
|
| 41 |
+
"che_Cyrl": 282762,
|
| 42 |
+
"cjk_Latn": 282763,
|
| 43 |
+
"ckb_Arab": 282764,
|
| 44 |
+
"crh_Latn": 282765,
|
| 45 |
+
"cym_Latn": 282766,
|
| 46 |
+
"dan_Latn": 282767,
|
| 47 |
+
"deu_Latn": 282768,
|
| 48 |
+
"dik_Latn": 282769,
|
| 49 |
+
"dyu_Latn": 282770,
|
| 50 |
+
"dzo_Tibt": 282771,
|
| 51 |
+
"ell_Grek": 282772,
|
| 52 |
+
"eng_Latn": 282773,
|
| 53 |
+
"epo_Latn": 282774,
|
| 54 |
+
"est_Latn": 282775,
|
| 55 |
+
"eus_Latn": 282776,
|
| 56 |
+
"ewe_Latn": 282777,
|
| 57 |
+
"fao_Latn": 282778,
|
| 58 |
+
"fij_Latn": 282779,
|
| 59 |
+
"fin_Latn": 282780,
|
| 60 |
+
"fon_Latn": 282781,
|
| 61 |
+
"fra_Latn": 282782,
|
| 62 |
+
"fur_Latn": 282783,
|
| 63 |
+
"fuv_Latn": 282784,
|
| 64 |
+
"gaz_Latn": 282785,
|
| 65 |
+
"gla_Latn": 282786,
|
| 66 |
+
"gle_Latn": 282787,
|
| 67 |
+
"glg_Latn": 282788,
|
| 68 |
+
"grn_Latn": 282789,
|
| 69 |
+
"guj_Gujr": 282790,
|
| 70 |
+
"hat_Latn": 282791,
|
| 71 |
+
"hau_Latn": 282792,
|
| 72 |
+
"heb_Hebr": 282793,
|
| 73 |
+
"hin_Deva": 282794,
|
| 74 |
+
"hne_Deva": 282795,
|
| 75 |
+
"hrv_Latn": 282796,
|
| 76 |
+
"hun_Latn": 282797,
|
| 77 |
+
"hye_Armn": 282798,
|
| 78 |
+
"ibo_Latn": 282799,
|
| 79 |
+
"ilo_Latn": 282800,
|
| 80 |
+
"ind_Latn": 282801,
|
| 81 |
+
"isl_Latn": 282802,
|
| 82 |
+
"ita_Latn": 282803,
|
| 83 |
+
"jav_Latn": 282804,
|
| 84 |
+
"jpn_Jpan": 282805,
|
| 85 |
+
"kab_Latn": 282806,
|
| 86 |
+
"kac_Latn": 282807,
|
| 87 |
+
"kam_Latn": 282808,
|
| 88 |
+
"kan_Knda": 282809,
|
| 89 |
+
"kas_Arab": 282810,
|
| 90 |
+
"kas_Deva": 282811,
|
| 91 |
+
"kat_Geor": 282812,
|
| 92 |
+
"kaz_Cyrl": 282813,
|
| 93 |
+
"kbp_Latn": 282814,
|
| 94 |
+
"kea_Latn": 282815,
|
| 95 |
+
"khk_Cyrl": 282816,
|
| 96 |
+
"khm_Khmr": 282817,
|
| 97 |
+
"kik_Latn": 282818,
|
| 98 |
+
"kin_Latn": 282819,
|
| 99 |
+
"kir_Cyrl": 282820,
|
| 100 |
+
"kmb_Latn": 282821,
|
| 101 |
+
"kmr_Latn": 282822,
|
| 102 |
+
"knc_Arab": 282823,
|
| 103 |
+
"knc_Latn": 282824,
|
| 104 |
+
"kon_Latn": 282825,
|
| 105 |
+
"kor_Hang": 282826,
|
| 106 |
+
"lao_Laoo": 282827,
|
| 107 |
+
"lij_Latn": 282828,
|
| 108 |
+
"lim_Latn": 282829,
|
| 109 |
+
"lin_Latn": 282830,
|
| 110 |
+
"lit_Latn": 282831,
|
| 111 |
+
"lmo_Latn": 282832,
|
| 112 |
+
"ltg_Latn": 282833,
|
| 113 |
+
"ltz_Latn": 282834,
|
| 114 |
+
"lua_Latn": 282835,
|
| 115 |
+
"lug_Latn": 282836,
|
| 116 |
+
"luo_Latn": 282837,
|
| 117 |
+
"lus_Latn": 282838,
|
| 118 |
+
"lvs_Latn": 282839,
|
| 119 |
+
"mag_Deva": 282840,
|
| 120 |
+
"mai_Deva": 282841,
|
| 121 |
+
"mal_Mlym": 282842,
|
| 122 |
+
"mar_Deva": 282843,
|
| 123 |
+
"min_Latn": 282844,
|
| 124 |
+
"mkd_Cyrl": 282845,
|
| 125 |
+
"mlt_Latn": 282846,
|
| 126 |
+
"mni_Beng": 282847,
|
| 127 |
+
"mos_Latn": 282848,
|
| 128 |
+
"mri_Latn": 282849,
|
| 129 |
+
"mya_Mymr": 282850,
|
| 130 |
+
"myv_Cyrl": 282851,
|
| 131 |
+
"nld_Latn": 282852,
|
| 132 |
+
"nno_Latn": 282853,
|
| 133 |
+
"nob_Latn": 282854,
|
| 134 |
+
"npi_Deva": 282855,
|
| 135 |
+
"nso_Latn": 282856,
|
| 136 |
+
"nus_Latn": 282857,
|
| 137 |
+
"nya_Latn": 282858,
|
| 138 |
+
"oci_Latn": 282859,
|
| 139 |
+
"ory_Orya": 282860,
|
| 140 |
+
"pag_Latn": 282861,
|
| 141 |
+
"pan_Guru": 282862,
|
| 142 |
+
"pap_Latn": 282863,
|
| 143 |
+
"pbt_Arab": 282864,
|
| 144 |
+
"pes_Arab": 282865,
|
| 145 |
+
"plt_Latn": 282866,
|
| 146 |
+
"pol_Latn": 282867,
|
| 147 |
+
"por_Latn": 282868,
|
| 148 |
+
"prs_Arab": 282869,
|
| 149 |
+
"quy_Latn": 282870,
|
| 150 |
+
"ron_Latn": 282871,
|
| 151 |
+
"run_Latn": 282872,
|
| 152 |
+
"rus_Cyrl": 282873,
|
| 153 |
+
"sag_Latn": 282874,
|
| 154 |
+
"san_Deva": 282875,
|
| 155 |
+
"sat_Beng": 282876,
|
| 156 |
+
"scn_Latn": 282877,
|
| 157 |
+
"shn_Mymr": 282878,
|
| 158 |
+
"sin_Sinh": 282879,
|
| 159 |
+
"slk_Latn": 282880,
|
| 160 |
+
"slv_Latn": 282881,
|
| 161 |
+
"smo_Latn": 282882,
|
| 162 |
+
"sna_Latn": 282883,
|
| 163 |
+
"snd_Arab": 282884,
|
| 164 |
+
"som_Latn": 282885,
|
| 165 |
+
"sot_Latn": 282886,
|
| 166 |
+
"spa_Latn": 282887,
|
| 167 |
+
"srd_Latn": 282888,
|
| 168 |
+
"srp_Cyrl": 282889,
|
| 169 |
+
"ssw_Latn": 282890,
|
| 170 |
+
"sun_Latn": 282891,
|
| 171 |
+
"swe_Latn": 282892,
|
| 172 |
+
"swh_Latn": 282893,
|
| 173 |
+
"szl_Latn": 282894,
|
| 174 |
+
"tam_Taml": 282895,
|
| 175 |
+
"taq_Latn": 282896,
|
| 176 |
+
"taq_Tfng": 282897,
|
| 177 |
+
"tat_Cyrl": 282898,
|
| 178 |
+
"tel_Telu": 282899,
|
| 179 |
+
"tgk_Cyrl": 282900,
|
| 180 |
+
"tgl_Latn": 282901,
|
| 181 |
+
"tha_Thai": 282902,
|
| 182 |
+
"tir_Ethi": 282903,
|
| 183 |
+
"tpi_Latn": 282904,
|
| 184 |
+
"tsn_Latn": 282905,
|
| 185 |
+
"tso_Latn": 282906,
|
| 186 |
+
"tuk_Latn": 282907,
|
| 187 |
+
"tum_Latn": 282908,
|
| 188 |
+
"tur_Latn": 282909,
|
| 189 |
+
"twi_Latn": 282910,
|
| 190 |
+
"tyv_Cyrl": 282911,
|
| 191 |
+
"tzm_Tfng": 282912,
|
| 192 |
+
"uig_Arab": 282913,
|
| 193 |
+
"ukr_Cyrl": 282914,
|
| 194 |
+
"umb_Latn": 282915,
|
| 195 |
+
"urd_Arab": 282916,
|
| 196 |
+
"uzn_Latn": 282917,
|
| 197 |
+
"vec_Latn": 282918,
|
| 198 |
+
"vie_Latn": 282919,
|
| 199 |
+
"war_Latn": 282920,
|
| 200 |
+
"wol_Latn": 282921,
|
| 201 |
+
"xho_Latn": 282922,
|
| 202 |
+
"ydd_Hebr": 282923,
|
| 203 |
+
"yor_Latn": 282924,
|
| 204 |
+
"yue_Hant": 282925,
|
| 205 |
+
"zho_Hans": 282926,
|
| 206 |
+
"zho_Hant": 282927,
|
| 207 |
+
"zsm_Latn": 282928,
|
| 208 |
+
"zul_Latn": 282929
|
| 209 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447fed75503655c842bfc0dc2a60920ba0ad13ea81528ff0b91c88a2ede2a70d
|
| 3 |
+
size 5488683
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"ace_Arab",
|
| 4 |
+
"ace_Latn",
|
| 5 |
+
"acm_Arab",
|
| 6 |
+
"acq_Arab",
|
| 7 |
+
"aeb_Arab",
|
| 8 |
+
"afr_Latn",
|
| 9 |
+
"ajp_Arab",
|
| 10 |
+
"aka_Latn",
|
| 11 |
+
"als_Latn",
|
| 12 |
+
"amh_Ethi",
|
| 13 |
+
"apc_Arab",
|
| 14 |
+
"arb_Arab",
|
| 15 |
+
"ars_Arab",
|
| 16 |
+
"ary_Arab",
|
| 17 |
+
"arz_Arab",
|
| 18 |
+
"asm_Beng",
|
| 19 |
+
"ast_Latn",
|
| 20 |
+
"awa_Deva",
|
| 21 |
+
"ayr_Latn",
|
| 22 |
+
"azb_Arab",
|
| 23 |
+
"azj_Latn",
|
| 24 |
+
"bak_Cyrl",
|
| 25 |
+
"bam_Latn",
|
| 26 |
+
"ban_Latn",
|
| 27 |
+
"bel_Cyrl",
|
| 28 |
+
"bem_Latn",
|
| 29 |
+
"ben_Beng",
|
| 30 |
+
"bho_Deva",
|
| 31 |
+
"bjn_Arab",
|
| 32 |
+
"bjn_Latn",
|
| 33 |
+
"bod_Tibt",
|
| 34 |
+
"bos_Latn",
|
| 35 |
+
"bug_Latn",
|
| 36 |
+
"bul_Cyrl",
|
| 37 |
+
"bxr_Cyrl",
|
| 38 |
+
"cat_Latn",
|
| 39 |
+
"ceb_Latn",
|
| 40 |
+
"ces_Latn",
|
| 41 |
+
"che_Cyrl",
|
| 42 |
+
"cjk_Latn",
|
| 43 |
+
"ckb_Arab",
|
| 44 |
+
"crh_Latn",
|
| 45 |
+
"cym_Latn",
|
| 46 |
+
"dan_Latn",
|
| 47 |
+
"deu_Latn",
|
| 48 |
+
"dik_Latn",
|
| 49 |
+
"dyu_Latn",
|
| 50 |
+
"dzo_Tibt",
|
| 51 |
+
"ell_Grek",
|
| 52 |
+
"eng_Latn",
|
| 53 |
+
"epo_Latn",
|
| 54 |
+
"est_Latn",
|
| 55 |
+
"eus_Latn",
|
| 56 |
+
"ewe_Latn",
|
| 57 |
+
"fao_Latn",
|
| 58 |
+
"fij_Latn",
|
| 59 |
+
"fin_Latn",
|
| 60 |
+
"fon_Latn",
|
| 61 |
+
"fra_Latn",
|
| 62 |
+
"fur_Latn",
|
| 63 |
+
"fuv_Latn",
|
| 64 |
+
"gaz_Latn",
|
| 65 |
+
"gla_Latn",
|
| 66 |
+
"gle_Latn",
|
| 67 |
+
"glg_Latn",
|
| 68 |
+
"grn_Latn",
|
| 69 |
+
"guj_Gujr",
|
| 70 |
+
"hat_Latn",
|
| 71 |
+
"hau_Latn",
|
| 72 |
+
"heb_Hebr",
|
| 73 |
+
"hin_Deva",
|
| 74 |
+
"hne_Deva",
|
| 75 |
+
"hrv_Latn",
|
| 76 |
+
"hun_Latn",
|
| 77 |
+
"hye_Armn",
|
| 78 |
+
"ibo_Latn",
|
| 79 |
+
"ilo_Latn",
|
| 80 |
+
"ind_Latn",
|
| 81 |
+
"isl_Latn",
|
| 82 |
+
"ita_Latn",
|
| 83 |
+
"jav_Latn",
|
| 84 |
+
"jpn_Jpan",
|
| 85 |
+
"kab_Latn",
|
| 86 |
+
"kac_Latn",
|
| 87 |
+
"kam_Latn",
|
| 88 |
+
"kan_Knda",
|
| 89 |
+
"kas_Arab",
|
| 90 |
+
"kas_Deva",
|
| 91 |
+
"kat_Geor",
|
| 92 |
+
"kaz_Cyrl",
|
| 93 |
+
"kbp_Latn",
|
| 94 |
+
"kea_Latn",
|
| 95 |
+
"khk_Cyrl",
|
| 96 |
+
"khm_Khmr",
|
| 97 |
+
"kik_Latn",
|
| 98 |
+
"kin_Latn",
|
| 99 |
+
"kir_Cyrl",
|
| 100 |
+
"kmb_Latn",
|
| 101 |
+
"kmr_Latn",
|
| 102 |
+
"knc_Arab",
|
| 103 |
+
"knc_Latn",
|
| 104 |
+
"kon_Latn",
|
| 105 |
+
"kor_Hang",
|
| 106 |
+
"lao_Laoo",
|
| 107 |
+
"lij_Latn",
|
| 108 |
+
"lim_Latn",
|
| 109 |
+
"lin_Latn",
|
| 110 |
+
"lit_Latn",
|
| 111 |
+
"lmo_Latn",
|
| 112 |
+
"ltg_Latn",
|
| 113 |
+
"ltz_Latn",
|
| 114 |
+
"lua_Latn",
|
| 115 |
+
"lug_Latn",
|
| 116 |
+
"luo_Latn",
|
| 117 |
+
"lus_Latn",
|
| 118 |
+
"lvs_Latn",
|
| 119 |
+
"mag_Deva",
|
| 120 |
+
"mai_Deva",
|
| 121 |
+
"mal_Mlym",
|
| 122 |
+
"mar_Deva",
|
| 123 |
+
"min_Latn",
|
| 124 |
+
"mkd_Cyrl",
|
| 125 |
+
"mlt_Latn",
|
| 126 |
+
"mni_Beng",
|
| 127 |
+
"mos_Latn",
|
| 128 |
+
"mri_Latn",
|
| 129 |
+
"mya_Mymr",
|
| 130 |
+
"myv_Cyrl",
|
| 131 |
+
"nld_Latn",
|
| 132 |
+
"nno_Latn",
|
| 133 |
+
"nob_Latn",
|
| 134 |
+
"npi_Deva",
|
| 135 |
+
"nso_Latn",
|
| 136 |
+
"nus_Latn",
|
| 137 |
+
"nya_Latn",
|
| 138 |
+
"oci_Latn",
|
| 139 |
+
"ory_Orya",
|
| 140 |
+
"pag_Latn",
|
| 141 |
+
"pan_Guru",
|
| 142 |
+
"pap_Latn",
|
| 143 |
+
"pbt_Arab",
|
| 144 |
+
"pes_Arab",
|
| 145 |
+
"plt_Latn",
|
| 146 |
+
"pol_Latn",
|
| 147 |
+
"por_Latn",
|
| 148 |
+
"prs_Arab",
|
| 149 |
+
"quy_Latn",
|
| 150 |
+
"ron_Latn",
|
| 151 |
+
"run_Latn",
|
| 152 |
+
"rus_Cyrl",
|
| 153 |
+
"sag_Latn",
|
| 154 |
+
"san_Deva",
|
| 155 |
+
"sat_Beng",
|
| 156 |
+
"scn_Latn",
|
| 157 |
+
"shn_Mymr",
|
| 158 |
+
"sin_Sinh",
|
| 159 |
+
"slk_Latn",
|
| 160 |
+
"slv_Latn",
|
| 161 |
+
"smo_Latn",
|
| 162 |
+
"sna_Latn",
|
| 163 |
+
"snd_Arab",
|
| 164 |
+
"som_Latn",
|
| 165 |
+
"sot_Latn",
|
| 166 |
+
"spa_Latn",
|
| 167 |
+
"srd_Latn",
|
| 168 |
+
"srp_Cyrl",
|
| 169 |
+
"ssw_Latn",
|
| 170 |
+
"sun_Latn",
|
| 171 |
+
"swe_Latn",
|
| 172 |
+
"swh_Latn",
|
| 173 |
+
"szl_Latn",
|
| 174 |
+
"tam_Taml",
|
| 175 |
+
"taq_Latn",
|
| 176 |
+
"taq_Tfng",
|
| 177 |
+
"tat_Cyrl",
|
| 178 |
+
"tel_Telu",
|
| 179 |
+
"tgk_Cyrl",
|
| 180 |
+
"tgl_Latn",
|
| 181 |
+
"tha_Thai",
|
| 182 |
+
"tir_Ethi",
|
| 183 |
+
"tpi_Latn",
|
| 184 |
+
"tsn_Latn",
|
| 185 |
+
"tso_Latn",
|
| 186 |
+
"tuk_Latn",
|
| 187 |
+
"tum_Latn",
|
| 188 |
+
"tur_Latn",
|
| 189 |
+
"twi_Latn",
|
| 190 |
+
"tyv_Cyrl",
|
| 191 |
+
"tzm_Tfng",
|
| 192 |
+
"uig_Arab",
|
| 193 |
+
"ukr_Cyrl",
|
| 194 |
+
"umb_Latn",
|
| 195 |
+
"urd_Arab",
|
| 196 |
+
"uzn_Latn",
|
| 197 |
+
"vec_Latn",
|
| 198 |
+
"vie_Latn",
|
| 199 |
+
"war_Latn",
|
| 200 |
+
"wol_Latn",
|
| 201 |
+
"xho_Latn",
|
| 202 |
+
"ydd_Hebr",
|
| 203 |
+
"yor_Latn",
|
| 204 |
+
"yue_Hant",
|
| 205 |
+
"zho_Hans",
|
| 206 |
+
"zho_Hant",
|
| 207 |
+
"zsm_Latn",
|
| 208 |
+
"zul_Latn"
|
| 209 |
+
],
|
| 210 |
+
"bos_token": {
|
| 211 |
+
"content": "<s>",
|
| 212 |
+
"lstrip": false,
|
| 213 |
+
"normalized": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"single_word": false
|
| 216 |
+
},
|
| 217 |
+
"cls_token": {
|
| 218 |
+
"content": "<s>",
|
| 219 |
+
"lstrip": false,
|
| 220 |
+
"normalized": false,
|
| 221 |
+
"rstrip": false,
|
| 222 |
+
"single_word": false
|
| 223 |
+
},
|
| 224 |
+
"eos_token": {
|
| 225 |
+
"content": "</s>",
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"normalized": false,
|
| 228 |
+
"rstrip": false,
|
| 229 |
+
"single_word": false
|
| 230 |
+
},
|
| 231 |
+
"mask_token": {
|
| 232 |
+
"content": "<mask>",
|
| 233 |
+
"lstrip": true,
|
| 234 |
+
"normalized": true,
|
| 235 |
+
"rstrip": false,
|
| 236 |
+
"single_word": false
|
| 237 |
+
},
|
| 238 |
+
"pad_token": {
|
| 239 |
+
"content": "<pad>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false
|
| 244 |
+
},
|
| 245 |
+
"sep_token": {
|
| 246 |
+
"content": "</s>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false
|
| 251 |
+
},
|
| 252 |
+
"unk_token": {
|
| 253 |
+
"content": "<unk>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false
|
| 258 |
+
}
|
| 259 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1914 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"282723": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"282724": {
|
| 44 |
+
"content": "ace_Arab",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"282725": {
|
| 52 |
+
"content": "ace_Latn",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"282726": {
|
| 60 |
+
"content": "acm_Arab",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"282727": {
|
| 68 |
+
"content": "acq_Arab",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"282728": {
|
| 76 |
+
"content": "aeb_Arab",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"282729": {
|
| 84 |
+
"content": "afr_Latn",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"282730": {
|
| 92 |
+
"content": "ajp_Arab",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"282731": {
|
| 100 |
+
"content": "aka_Latn",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"282732": {
|
| 108 |
+
"content": "als_Latn",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"282733": {
|
| 116 |
+
"content": "amh_Ethi",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"282734": {
|
| 124 |
+
"content": "apc_Arab",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"282735": {
|
| 132 |
+
"content": "arb_Arab",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"282736": {
|
| 140 |
+
"content": "ars_Arab",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"282737": {
|
| 148 |
+
"content": "ary_Arab",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"282738": {
|
| 156 |
+
"content": "arz_Arab",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"282739": {
|
| 164 |
+
"content": "asm_Beng",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"282740": {
|
| 172 |
+
"content": "ast_Latn",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"282741": {
|
| 180 |
+
"content": "awa_Deva",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"282742": {
|
| 188 |
+
"content": "ayr_Latn",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"282743": {
|
| 196 |
+
"content": "azb_Arab",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"282744": {
|
| 204 |
+
"content": "azj_Latn",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"282745": {
|
| 212 |
+
"content": "bak_Cyrl",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"282746": {
|
| 220 |
+
"content": "bam_Latn",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"282747": {
|
| 228 |
+
"content": "ban_Latn",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"282748": {
|
| 236 |
+
"content": "bel_Cyrl",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"282749": {
|
| 244 |
+
"content": "bem_Latn",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"282750": {
|
| 252 |
+
"content": "ben_Beng",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"282751": {
|
| 260 |
+
"content": "bho_Deva",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"282752": {
|
| 268 |
+
"content": "bjn_Arab",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"282753": {
|
| 276 |
+
"content": "bjn_Latn",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"282754": {
|
| 284 |
+
"content": "bod_Tibt",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"282755": {
|
| 292 |
+
"content": "bos_Latn",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"282756": {
|
| 300 |
+
"content": "bug_Latn",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"282757": {
|
| 308 |
+
"content": "bul_Cyrl",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"282758": {
|
| 316 |
+
"content": "bxr_Cyrl",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"282759": {
|
| 324 |
+
"content": "cat_Latn",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"282760": {
|
| 332 |
+
"content": "ceb_Latn",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"282761": {
|
| 340 |
+
"content": "ces_Latn",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"282762": {
|
| 348 |
+
"content": "che_Cyrl",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"282763": {
|
| 356 |
+
"content": "cjk_Latn",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"282764": {
|
| 364 |
+
"content": "ckb_Arab",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"282765": {
|
| 372 |
+
"content": "crh_Latn",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"282766": {
|
| 380 |
+
"content": "cym_Latn",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"282767": {
|
| 388 |
+
"content": "dan_Latn",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"282768": {
|
| 396 |
+
"content": "deu_Latn",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"282769": {
|
| 404 |
+
"content": "dik_Latn",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"282770": {
|
| 412 |
+
"content": "dyu_Latn",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"282771": {
|
| 420 |
+
"content": "dzo_Tibt",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"282772": {
|
| 428 |
+
"content": "ell_Grek",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"282773": {
|
| 436 |
+
"content": "eng_Latn",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"282774": {
|
| 444 |
+
"content": "epo_Latn",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"282775": {
|
| 452 |
+
"content": "est_Latn",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"282776": {
|
| 460 |
+
"content": "eus_Latn",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"282777": {
|
| 468 |
+
"content": "ewe_Latn",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"282778": {
|
| 476 |
+
"content": "fao_Latn",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"282779": {
|
| 484 |
+
"content": "fij_Latn",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"282780": {
|
| 492 |
+
"content": "fin_Latn",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"282781": {
|
| 500 |
+
"content": "fon_Latn",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"282782": {
|
| 508 |
+
"content": "fra_Latn",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"282783": {
|
| 516 |
+
"content": "fur_Latn",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"282784": {
|
| 524 |
+
"content": "fuv_Latn",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"282785": {
|
| 532 |
+
"content": "gaz_Latn",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"282786": {
|
| 540 |
+
"content": "gla_Latn",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"282787": {
|
| 548 |
+
"content": "gle_Latn",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"282788": {
|
| 556 |
+
"content": "glg_Latn",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"282789": {
|
| 564 |
+
"content": "grn_Latn",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"282790": {
|
| 572 |
+
"content": "guj_Gujr",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"282791": {
|
| 580 |
+
"content": "hat_Latn",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"282792": {
|
| 588 |
+
"content": "hau_Latn",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"282793": {
|
| 596 |
+
"content": "heb_Hebr",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"282794": {
|
| 604 |
+
"content": "hin_Deva",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"282795": {
|
| 612 |
+
"content": "hne_Deva",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"282796": {
|
| 620 |
+
"content": "hrv_Latn",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"282797": {
|
| 628 |
+
"content": "hun_Latn",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"282798": {
|
| 636 |
+
"content": "hye_Armn",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"282799": {
|
| 644 |
+
"content": "ibo_Latn",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"282800": {
|
| 652 |
+
"content": "ilo_Latn",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"282801": {
|
| 660 |
+
"content": "ind_Latn",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"282802": {
|
| 668 |
+
"content": "isl_Latn",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"282803": {
|
| 676 |
+
"content": "ita_Latn",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"282804": {
|
| 684 |
+
"content": "jav_Latn",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"282805": {
|
| 692 |
+
"content": "jpn_Jpan",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"282806": {
|
| 700 |
+
"content": "kab_Latn",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"282807": {
|
| 708 |
+
"content": "kac_Latn",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"282808": {
|
| 716 |
+
"content": "kam_Latn",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"282809": {
|
| 724 |
+
"content": "kan_Knda",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"282810": {
|
| 732 |
+
"content": "kas_Arab",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"282811": {
|
| 740 |
+
"content": "kas_Deva",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"282812": {
|
| 748 |
+
"content": "kat_Geor",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"282813": {
|
| 756 |
+
"content": "kaz_Cyrl",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"282814": {
|
| 764 |
+
"content": "kbp_Latn",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"282815": {
|
| 772 |
+
"content": "kea_Latn",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"282816": {
|
| 780 |
+
"content": "khk_Cyrl",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"282817": {
|
| 788 |
+
"content": "khm_Khmr",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"282818": {
|
| 796 |
+
"content": "kik_Latn",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"282819": {
|
| 804 |
+
"content": "kin_Latn",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"282820": {
|
| 812 |
+
"content": "kir_Cyrl",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"282821": {
|
| 820 |
+
"content": "kmb_Latn",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"282822": {
|
| 828 |
+
"content": "kmr_Latn",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"282823": {
|
| 836 |
+
"content": "knc_Arab",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"282824": {
|
| 844 |
+
"content": "knc_Latn",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"282825": {
|
| 852 |
+
"content": "kon_Latn",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"282826": {
|
| 860 |
+
"content": "kor_Hang",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"282827": {
|
| 868 |
+
"content": "lao_Laoo",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"282828": {
|
| 876 |
+
"content": "lij_Latn",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"282829": {
|
| 884 |
+
"content": "lim_Latn",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"282830": {
|
| 892 |
+
"content": "lin_Latn",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"282831": {
|
| 900 |
+
"content": "lit_Latn",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"282832": {
|
| 908 |
+
"content": "lmo_Latn",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"282833": {
|
| 916 |
+
"content": "ltg_Latn",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"282834": {
|
| 924 |
+
"content": "ltz_Latn",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"282835": {
|
| 932 |
+
"content": "lua_Latn",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"282836": {
|
| 940 |
+
"content": "lug_Latn",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"282837": {
|
| 948 |
+
"content": "luo_Latn",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"282838": {
|
| 956 |
+
"content": "lus_Latn",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"282839": {
|
| 964 |
+
"content": "lvs_Latn",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"282840": {
|
| 972 |
+
"content": "mag_Deva",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"282841": {
|
| 980 |
+
"content": "mai_Deva",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"282842": {
|
| 988 |
+
"content": "mal_Mlym",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"282843": {
|
| 996 |
+
"content": "mar_Deva",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"282844": {
|
| 1004 |
+
"content": "min_Latn",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"282845": {
|
| 1012 |
+
"content": "mkd_Cyrl",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"282846": {
|
| 1020 |
+
"content": "mlt_Latn",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"282847": {
|
| 1028 |
+
"content": "mni_Beng",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"282848": {
|
| 1036 |
+
"content": "mos_Latn",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"282849": {
|
| 1044 |
+
"content": "mri_Latn",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"282850": {
|
| 1052 |
+
"content": "mya_Mymr",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"282851": {
|
| 1060 |
+
"content": "myv_Cyrl",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"282852": {
|
| 1068 |
+
"content": "nld_Latn",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"282853": {
|
| 1076 |
+
"content": "nno_Latn",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"282854": {
|
| 1084 |
+
"content": "nob_Latn",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"282855": {
|
| 1092 |
+
"content": "npi_Deva",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"282856": {
|
| 1100 |
+
"content": "nso_Latn",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"282857": {
|
| 1108 |
+
"content": "nus_Latn",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"282858": {
|
| 1116 |
+
"content": "nya_Latn",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"282859": {
|
| 1124 |
+
"content": "oci_Latn",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"282860": {
|
| 1132 |
+
"content": "ory_Orya",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"282861": {
|
| 1140 |
+
"content": "pag_Latn",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"282862": {
|
| 1148 |
+
"content": "pan_Guru",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"282863": {
|
| 1156 |
+
"content": "pap_Latn",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"282864": {
|
| 1164 |
+
"content": "pbt_Arab",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"282865": {
|
| 1172 |
+
"content": "pes_Arab",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"282866": {
|
| 1180 |
+
"content": "plt_Latn",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"282867": {
|
| 1188 |
+
"content": "pol_Latn",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"282868": {
|
| 1196 |
+
"content": "por_Latn",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"282869": {
|
| 1204 |
+
"content": "prs_Arab",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"282870": {
|
| 1212 |
+
"content": "quy_Latn",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"282871": {
|
| 1220 |
+
"content": "ron_Latn",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"282872": {
|
| 1228 |
+
"content": "run_Latn",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"282873": {
|
| 1236 |
+
"content": "rus_Cyrl",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"282874": {
|
| 1244 |
+
"content": "sag_Latn",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"282875": {
|
| 1252 |
+
"content": "san_Deva",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"282876": {
|
| 1260 |
+
"content": "sat_Beng",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"282877": {
|
| 1268 |
+
"content": "scn_Latn",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"282878": {
|
| 1276 |
+
"content": "shn_Mymr",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"282879": {
|
| 1284 |
+
"content": "sin_Sinh",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"282880": {
|
| 1292 |
+
"content": "slk_Latn",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"282881": {
|
| 1300 |
+
"content": "slv_Latn",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"282882": {
|
| 1308 |
+
"content": "smo_Latn",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"282883": {
|
| 1316 |
+
"content": "sna_Latn",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"282884": {
|
| 1324 |
+
"content": "snd_Arab",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"282885": {
|
| 1332 |
+
"content": "som_Latn",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"282886": {
|
| 1340 |
+
"content": "sot_Latn",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"282887": {
|
| 1348 |
+
"content": "spa_Latn",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"282888": {
|
| 1356 |
+
"content": "srd_Latn",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"282889": {
|
| 1364 |
+
"content": "srp_Cyrl",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"282890": {
|
| 1372 |
+
"content": "ssw_Latn",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"282891": {
|
| 1380 |
+
"content": "sun_Latn",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"282892": {
|
| 1388 |
+
"content": "swe_Latn",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"282893": {
|
| 1396 |
+
"content": "swh_Latn",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"282894": {
|
| 1404 |
+
"content": "szl_Latn",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"282895": {
|
| 1412 |
+
"content": "tam_Taml",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"282896": {
|
| 1420 |
+
"content": "taq_Latn",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"282897": {
|
| 1428 |
+
"content": "taq_Tfng",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"282898": {
|
| 1436 |
+
"content": "tat_Cyrl",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"282899": {
|
| 1444 |
+
"content": "tel_Telu",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"282900": {
|
| 1452 |
+
"content": "tgk_Cyrl",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"282901": {
|
| 1460 |
+
"content": "tgl_Latn",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"282902": {
|
| 1468 |
+
"content": "tha_Thai",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"282903": {
|
| 1476 |
+
"content": "tir_Ethi",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"282904": {
|
| 1484 |
+
"content": "tpi_Latn",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"282905": {
|
| 1492 |
+
"content": "tsn_Latn",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"282906": {
|
| 1500 |
+
"content": "tso_Latn",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"282907": {
|
| 1508 |
+
"content": "tuk_Latn",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"282908": {
|
| 1516 |
+
"content": "tum_Latn",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"282909": {
|
| 1524 |
+
"content": "tur_Latn",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"282910": {
|
| 1532 |
+
"content": "twi_Latn",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"282911": {
|
| 1540 |
+
"content": "tyv_Cyrl",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"282912": {
|
| 1548 |
+
"content": "tzm_Tfng",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"282913": {
|
| 1556 |
+
"content": "uig_Arab",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"282914": {
|
| 1564 |
+
"content": "ukr_Cyrl",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"282915": {
|
| 1572 |
+
"content": "umb_Latn",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"282916": {
|
| 1580 |
+
"content": "urd_Arab",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"282917": {
|
| 1588 |
+
"content": "uzn_Latn",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"282918": {
|
| 1596 |
+
"content": "vec_Latn",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"282919": {
|
| 1604 |
+
"content": "vie_Latn",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"282920": {
|
| 1612 |
+
"content": "war_Latn",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"282921": {
|
| 1620 |
+
"content": "wol_Latn",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"282922": {
|
| 1628 |
+
"content": "xho_Latn",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"282923": {
|
| 1636 |
+
"content": "ydd_Hebr",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"282924": {
|
| 1644 |
+
"content": "yor_Latn",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"282925": {
|
| 1652 |
+
"content": "yue_Hant",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"282926": {
|
| 1660 |
+
"content": "zho_Hans",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"282927": {
|
| 1668 |
+
"content": "zho_Hant",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"282928": {
|
| 1676 |
+
"content": "zsm_Latn",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"282929": {
|
| 1684 |
+
"content": "zul_Latn",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
}
|
| 1691 |
+
},
|
| 1692 |
+
"additional_special_tokens": [
|
| 1693 |
+
"ace_Arab",
|
| 1694 |
+
"ace_Latn",
|
| 1695 |
+
"acm_Arab",
|
| 1696 |
+
"acq_Arab",
|
| 1697 |
+
"aeb_Arab",
|
| 1698 |
+
"afr_Latn",
|
| 1699 |
+
"ajp_Arab",
|
| 1700 |
+
"aka_Latn",
|
| 1701 |
+
"als_Latn",
|
| 1702 |
+
"amh_Ethi",
|
| 1703 |
+
"apc_Arab",
|
| 1704 |
+
"arb_Arab",
|
| 1705 |
+
"ars_Arab",
|
| 1706 |
+
"ary_Arab",
|
| 1707 |
+
"arz_Arab",
|
| 1708 |
+
"asm_Beng",
|
| 1709 |
+
"ast_Latn",
|
| 1710 |
+
"awa_Deva",
|
| 1711 |
+
"ayr_Latn",
|
| 1712 |
+
"azb_Arab",
|
| 1713 |
+
"azj_Latn",
|
| 1714 |
+
"bak_Cyrl",
|
| 1715 |
+
"bam_Latn",
|
| 1716 |
+
"ban_Latn",
|
| 1717 |
+
"bel_Cyrl",
|
| 1718 |
+
"bem_Latn",
|
| 1719 |
+
"ben_Beng",
|
| 1720 |
+
"bho_Deva",
|
| 1721 |
+
"bjn_Arab",
|
| 1722 |
+
"bjn_Latn",
|
| 1723 |
+
"bod_Tibt",
|
| 1724 |
+
"bos_Latn",
|
| 1725 |
+
"bug_Latn",
|
| 1726 |
+
"bul_Cyrl",
|
| 1727 |
+
"bxr_Cyrl",
|
| 1728 |
+
"cat_Latn",
|
| 1729 |
+
"ceb_Latn",
|
| 1730 |
+
"ces_Latn",
|
| 1731 |
+
"che_Cyrl",
|
| 1732 |
+
"cjk_Latn",
|
| 1733 |
+
"ckb_Arab",
|
| 1734 |
+
"crh_Latn",
|
| 1735 |
+
"cym_Latn",
|
| 1736 |
+
"dan_Latn",
|
| 1737 |
+
"deu_Latn",
|
| 1738 |
+
"dik_Latn",
|
| 1739 |
+
"dyu_Latn",
|
| 1740 |
+
"dzo_Tibt",
|
| 1741 |
+
"ell_Grek",
|
| 1742 |
+
"eng_Latn",
|
| 1743 |
+
"epo_Latn",
|
| 1744 |
+
"est_Latn",
|
| 1745 |
+
"eus_Latn",
|
| 1746 |
+
"ewe_Latn",
|
| 1747 |
+
"fao_Latn",
|
| 1748 |
+
"fij_Latn",
|
| 1749 |
+
"fin_Latn",
|
| 1750 |
+
"fon_Latn",
|
| 1751 |
+
"fra_Latn",
|
| 1752 |
+
"fur_Latn",
|
| 1753 |
+
"fuv_Latn",
|
| 1754 |
+
"gaz_Latn",
|
| 1755 |
+
"gla_Latn",
|
| 1756 |
+
"gle_Latn",
|
| 1757 |
+
"glg_Latn",
|
| 1758 |
+
"grn_Latn",
|
| 1759 |
+
"guj_Gujr",
|
| 1760 |
+
"hat_Latn",
|
| 1761 |
+
"hau_Latn",
|
| 1762 |
+
"heb_Hebr",
|
| 1763 |
+
"hin_Deva",
|
| 1764 |
+
"hne_Deva",
|
| 1765 |
+
"hrv_Latn",
|
| 1766 |
+
"hun_Latn",
|
| 1767 |
+
"hye_Armn",
|
| 1768 |
+
"ibo_Latn",
|
| 1769 |
+
"ilo_Latn",
|
| 1770 |
+
"ind_Latn",
|
| 1771 |
+
"isl_Latn",
|
| 1772 |
+
"ita_Latn",
|
| 1773 |
+
"jav_Latn",
|
| 1774 |
+
"jpn_Jpan",
|
| 1775 |
+
"kab_Latn",
|
| 1776 |
+
"kac_Latn",
|
| 1777 |
+
"kam_Latn",
|
| 1778 |
+
"kan_Knda",
|
| 1779 |
+
"kas_Arab",
|
| 1780 |
+
"kas_Deva",
|
| 1781 |
+
"kat_Geor",
|
| 1782 |
+
"kaz_Cyrl",
|
| 1783 |
+
"kbp_Latn",
|
| 1784 |
+
"kea_Latn",
|
| 1785 |
+
"khk_Cyrl",
|
| 1786 |
+
"khm_Khmr",
|
| 1787 |
+
"kik_Latn",
|
| 1788 |
+
"kin_Latn",
|
| 1789 |
+
"kir_Cyrl",
|
| 1790 |
+
"kmb_Latn",
|
| 1791 |
+
"kmr_Latn",
|
| 1792 |
+
"knc_Arab",
|
| 1793 |
+
"knc_Latn",
|
| 1794 |
+
"kon_Latn",
|
| 1795 |
+
"kor_Hang",
|
| 1796 |
+
"lao_Laoo",
|
| 1797 |
+
"lij_Latn",
|
| 1798 |
+
"lim_Latn",
|
| 1799 |
+
"lin_Latn",
|
| 1800 |
+
"lit_Latn",
|
| 1801 |
+
"lmo_Latn",
|
| 1802 |
+
"ltg_Latn",
|
| 1803 |
+
"ltz_Latn",
|
| 1804 |
+
"lua_Latn",
|
| 1805 |
+
"lug_Latn",
|
| 1806 |
+
"luo_Latn",
|
| 1807 |
+
"lus_Latn",
|
| 1808 |
+
"lvs_Latn",
|
| 1809 |
+
"mag_Deva",
|
| 1810 |
+
"mai_Deva",
|
| 1811 |
+
"mal_Mlym",
|
| 1812 |
+
"mar_Deva",
|
| 1813 |
+
"min_Latn",
|
| 1814 |
+
"mkd_Cyrl",
|
| 1815 |
+
"mlt_Latn",
|
| 1816 |
+
"mni_Beng",
|
| 1817 |
+
"mos_Latn",
|
| 1818 |
+
"mri_Latn",
|
| 1819 |
+
"mya_Mymr",
|
| 1820 |
+
"myv_Cyrl",
|
| 1821 |
+
"nld_Latn",
|
| 1822 |
+
"nno_Latn",
|
| 1823 |
+
"nob_Latn",
|
| 1824 |
+
"npi_Deva",
|
| 1825 |
+
"nso_Latn",
|
| 1826 |
+
"nus_Latn",
|
| 1827 |
+
"nya_Latn",
|
| 1828 |
+
"oci_Latn",
|
| 1829 |
+
"ory_Orya",
|
| 1830 |
+
"pag_Latn",
|
| 1831 |
+
"pan_Guru",
|
| 1832 |
+
"pap_Latn",
|
| 1833 |
+
"pbt_Arab",
|
| 1834 |
+
"pes_Arab",
|
| 1835 |
+
"plt_Latn",
|
| 1836 |
+
"pol_Latn",
|
| 1837 |
+
"por_Latn",
|
| 1838 |
+
"prs_Arab",
|
| 1839 |
+
"quy_Latn",
|
| 1840 |
+
"ron_Latn",
|
| 1841 |
+
"run_Latn",
|
| 1842 |
+
"rus_Cyrl",
|
| 1843 |
+
"sag_Latn",
|
| 1844 |
+
"san_Deva",
|
| 1845 |
+
"sat_Beng",
|
| 1846 |
+
"scn_Latn",
|
| 1847 |
+
"shn_Mymr",
|
| 1848 |
+
"sin_Sinh",
|
| 1849 |
+
"slk_Latn",
|
| 1850 |
+
"slv_Latn",
|
| 1851 |
+
"smo_Latn",
|
| 1852 |
+
"sna_Latn",
|
| 1853 |
+
"snd_Arab",
|
| 1854 |
+
"som_Latn",
|
| 1855 |
+
"sot_Latn",
|
| 1856 |
+
"spa_Latn",
|
| 1857 |
+
"srd_Latn",
|
| 1858 |
+
"srp_Cyrl",
|
| 1859 |
+
"ssw_Latn",
|
| 1860 |
+
"sun_Latn",
|
| 1861 |
+
"swe_Latn",
|
| 1862 |
+
"swh_Latn",
|
| 1863 |
+
"szl_Latn",
|
| 1864 |
+
"tam_Taml",
|
| 1865 |
+
"taq_Latn",
|
| 1866 |
+
"taq_Tfng",
|
| 1867 |
+
"tat_Cyrl",
|
| 1868 |
+
"tel_Telu",
|
| 1869 |
+
"tgk_Cyrl",
|
| 1870 |
+
"tgl_Latn",
|
| 1871 |
+
"tha_Thai",
|
| 1872 |
+
"tir_Ethi",
|
| 1873 |
+
"tpi_Latn",
|
| 1874 |
+
"tsn_Latn",
|
| 1875 |
+
"tso_Latn",
|
| 1876 |
+
"tuk_Latn",
|
| 1877 |
+
"tum_Latn",
|
| 1878 |
+
"tur_Latn",
|
| 1879 |
+
"twi_Latn",
|
| 1880 |
+
"tyv_Cyrl",
|
| 1881 |
+
"tzm_Tfng",
|
| 1882 |
+
"uig_Arab",
|
| 1883 |
+
"ukr_Cyrl",
|
| 1884 |
+
"umb_Latn",
|
| 1885 |
+
"urd_Arab",
|
| 1886 |
+
"uzn_Latn",
|
| 1887 |
+
"vec_Latn",
|
| 1888 |
+
"vie_Latn",
|
| 1889 |
+
"war_Latn",
|
| 1890 |
+
"wol_Latn",
|
| 1891 |
+
"xho_Latn",
|
| 1892 |
+
"ydd_Hebr",
|
| 1893 |
+
"yor_Latn",
|
| 1894 |
+
"yue_Hant",
|
| 1895 |
+
"zho_Hans",
|
| 1896 |
+
"zho_Hant",
|
| 1897 |
+
"zsm_Latn",
|
| 1898 |
+
"zul_Latn"
|
| 1899 |
+
],
|
| 1900 |
+
"bos_token": "<s>",
|
| 1901 |
+
"clean_up_tokenization_spaces": true,
|
| 1902 |
+
"cls_token": "<s>",
|
| 1903 |
+
"eos_token": "</s>",
|
| 1904 |
+
"legacy_behaviour": false,
|
| 1905 |
+
"mask_token": "<mask>",
|
| 1906 |
+
"model_max_length": 1024,
|
| 1907 |
+
"pad_token": "<pad>",
|
| 1908 |
+
"sep_token": "</s>",
|
| 1909 |
+
"sp_model_kwargs": {},
|
| 1910 |
+
"src_lang": "myv_Cyrl",
|
| 1911 |
+
"tgt_lang": "rus_Cyrl",
|
| 1912 |
+
"tokenizer_class": "NllbTokenizer",
|
| 1913 |
+
"unk_token": "<unk>"
|
| 1914 |
+
}
|