CommonLingua / lang2idx.json
Pclanglais's picture
v7.2.1-ngram release: fp32 + bf16 weights, model.py, predict.py, model card
d988f49 verified
{
"abk": 0,
"ace": 1,
"ach": 2,
"ady": 3,
"afr": 4,
"aka": 5,
"akk": 6,
"alt": 7,
"amh": 8,
"ami": 9,
"ang": 10,
"anp": 11,
"arb": 12,
"arc": 13,
"arg": 14,
"arq": 15,
"ary": 16,
"arz": 17,
"asm": 18,
"ast": 19,
"atj": 20,
"ava": 21,
"avk": 22,
"awa": 23,
"aym": 24,
"azb": 25,
"azj": 26,
"bak": 27,
"bam": 28,
"ban": 29,
"bar": 30,
"bbc": 31,
"bel": 32,
"ben": 33,
"bho": 34,
"bik": 35,
"bis": 36,
"bjn": 37,
"blk": 38,
"bod": 39,
"bos": 40,
"bpy": 41,
"bre": 42,
"bug": 43,
"bul": 44,
"bxr": 45,
"cat": 46,
"cbk": 47,
"cdo": 48,
"ceb": 49,
"ces": 50,
"che": 51,
"chr": 52,
"chu": 53,
"chv": 54,
"chy": 55,
"ckb": 56,
"cor": 57,
"cos": 58,
"crh": 59,
"csb": 60,
"cym": 61,
"dag": 62,
"dan": 63,
"deu": 64,
"din": 65,
"diq": 66,
"div": 67,
"dsb": 68,
"dty": 69,
"dzo": 70,
"egx": 71,
"egy": 72,
"ell": 73,
"eml": 74,
"eng": 75,
"epo": 76,
"est": 77,
"ett": 78,
"eus": 79,
"ewe": 80,
"ext": 81,
"fao": 82,
"fas": 83,
"fij": 84,
"fin": 85,
"fon": 86,
"fra": 87,
"fro": 88,
"frp": 89,
"frr": 90,
"fry": 91,
"ful": 92,
"fur": 93,
"gag": 94,
"gan": 95,
"gaz": 96,
"gcr": 97,
"gez": 98,
"gla": 99,
"gle": 100,
"glg": 101,
"glk": 102,
"glv": 103,
"gom": 104,
"gor": 105,
"got": 106,
"gpe": 107,
"grc": 108,
"gsw": 109,
"guc": 110,
"gug": 111,
"guj": 112,
"gur": 113,
"guw": 114,
"hak": 115,
"hat": 116,
"hau": 117,
"haw": 118,
"hbo": 119,
"hbs": 120,
"heb": 121,
"hif": 122,
"hin": 123,
"hrv": 124,
"hsb": 125,
"hun": 126,
"hye": 127,
"hyw": 128,
"ibo": 129,
"ido": 130,
"iku": 131,
"ile": 132,
"ilo": 133,
"ina": 134,
"ind": 135,
"inh": 136,
"ipk": 137,
"isl": 138,
"ita": 139,
"jam": 140,
"jav": 141,
"jbo": 142,
"jpn": 143,
"kaa": 144,
"kab": 145,
"kal": 146,
"kan": 147,
"kas": 148,
"kat": 149,
"kaz": 150,
"kbd": 151,
"kbp": 152,
"kcg": 153,
"khk": 154,
"khm": 155,
"kik": 156,
"kin": 157,
"kir": 158,
"kmr": 159,
"koi": 160,
"kom": 161,
"kon": 162,
"kor": 163,
"krc": 164,
"ksh": 165,
"lad": 166,
"lao": 167,
"lat": 168,
"latex": 169,
"lav": 170,
"lbe": 171,
"lez": 172,
"lfn": 173,
"lij": 174,
"lim": 175,
"lin": 176,
"lit": 177,
"lld": 178,
"lmo": 179,
"ltg": 180,
"ltz": 181,
"lug": 182,
"luo": 183,
"lzh": 184,
"mad": 185,
"mai": 186,
"mal": 187,
"mar": 188,
"mdf": 189,
"mhr": 190,
"min": 191,
"mkd": 192,
"mlg": 193,
"mlt": 194,
"mni": 195,
"mnw": 196,
"mri": 197,
"mrj": 198,
"msa": 199,
"mwl": 200,
"mya": 201,
"myv": 202,
"mzn": 203,
"nah": 204,
"nan": 205,
"nap": 206,
"nav": 207,
"nds": 208,
"nep": 209,
"new": 210,
"nia": 211,
"nld": 212,
"nno": 213,
"nor": 214,
"nov": 215,
"nqo": 216,
"nrf": 217,
"nso": 218,
"nya": 219,
"nyn": 220,
"oci": 221,
"olo": 222,
"orm": 223,
"ory": 224,
"oss": 225,
"pag": 226,
"pam": 227,
"pan": 228,
"pap": 229,
"pcd": 230,
"pcm": 231,
"pdc": 232,
"peo": 233,
"pfl": 234,
"pms": 235,
"pnb": 236,
"pnt": 237,
"pol": 238,
"por": 239,
"pus": 240,
"pwn": 241,
"quy": 242,
"rcf": 243,
"rmy": 244,
"roh": 245,
"ron": 246,
"rue": 247,
"run": 248,
"rup": 249,
"rus": 250,
"sah": 251,
"san": 252,
"sat": 253,
"scn": 254,
"sgs": 255,
"shi": 256,
"shn": 257,
"sin": 258,
"skr": 259,
"slk": 260,
"slv": 261,
"sme": 262,
"smn": 263,
"smo": 264,
"sna": 265,
"snd": 266,
"som": 267,
"sot": 268,
"spa": 269,
"sqi": 270,
"srd": 271,
"srn": 272,
"srp": 273,
"ssw": 274,
"stq": 275,
"sun": 276,
"sux": 277,
"swe": 278,
"swh": 279,
"szl": 280,
"szy": 281,
"tah": 282,
"tam": 283,
"tat": 284,
"tay": 285,
"tcy": 286,
"tel": 287,
"tet": 288,
"tgk": 289,
"tgl": 290,
"tha": 291,
"tir": 292,
"tly": 293,
"ton": 294,
"tpi": 295,
"trv": 296,
"tsn": 297,
"tso": 298,
"tuk": 299,
"tum": 300,
"tur": 301,
"txb": 302,
"tyv": 303,
"udm": 304,
"uig": 305,
"ukr": 306,
"urd": 307,
"uzb": 308,
"vec": 309,
"ven": 310,
"vep": 311,
"vie": 312,
"vls": 313,
"vol": 314,
"vro": 315,
"war": 316,
"wln": 317,
"wol": 318,
"wuu": 319,
"xal": 320,
"xcl": 321,
"xho": 322,
"xmf": 323,
"xog": 324,
"xto": 325,
"ydd": 326,
"yor": 327,
"yue": 328,
"zea": 329,
"zgh": 330,
"zha": 331,
"zho": 332,
"zul": 333
}