diallomama
/

wav2vec2-common_voice-fr-training

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Community

wav2vec2-common_voice-fr-training / vocab.json

diallomama's picture

tokenizer and vocab (from up)

2e00fbe about 1 year ago

raw history blame contribute delete

4.04 kB

	{
	"!": 1,
	"\"": 2,
	"$": 3,
	"%": 4,
	"&": 5,
	"'": 6,
	"(": 7,
	")": 8,
	"*": 9,
	",": 10,
	"-": 11,
	".": 12,
	"/": 13,
	":": 14,
	";": 15,
	"=": 16,
	"?": 17,
	"[PAD]": 314,
	"[UNK]": 313,
	"^": 18,
	"_": 19,
	"`": 20,
	"a": 21,
	"b": 22,
	"c": 23,
	"d": 24,
	"e": 25,
	"f": 26,
	"g": 27,
	"h": 28,
	"i": 29,
	"j": 30,
	"k": 31,
	"l": 32,
	"m": 33,
	"n": 34,
	"o": 35,
	"p": 36,
	"q": 37,
	"r": 38,
	"s": 39,
	"t": 40,
	"u": 41,
	"v": 42,
	"w": 43,
	"x": 44,
	"y": 45,
	"z": 46,
	"{": 47,
	"\|": 0,
	"}": 49,
	"~": 50,
	"£": 51,
	"§": 52,
	"«": 53,
	"®": 54,
	"°": 55,
	"±": 56,
	"´": 57,
	"µ": 58,
	"·": 59,
	"º": 60,
	"»": 61,
	"½": 62,
	"×": 63,
	"ß": 64,
	"à": 65,
	"á": 66,
	"â": 67,
	"ã": 68,
	"ä": 69,
	"å": 70,
	"æ": 71,
	"ç": 72,
	"è": 73,
	"é": 74,
	"ê": 75,
	"ë": 76,
	"ì": 77,
	"í": 78,
	"î": 79,
	"ï": 80,
	"ð": 81,
	"ñ": 82,
	"ò": 83,
	"ó": 84,
	"ô": 85,
	"õ": 86,
	"ö": 87,
	"ø": 88,
	"ù": 89,
	"ú": 90,
	"û": 91,
	"ü": 92,
	"ý": 93,
	"þ": 94,
	"ÿ": 95,
	"ā": 96,
	"ă": 97,
	"ą": 98,
	"ć": 99,
	"ċ": 100,
	"č": 101,
	"ď": 102,
	"đ": 103,
	"ē": 104,
	"ė": 105,
	"ę": 106,
	"ě": 107,
	"ğ": 108,
	"ġ": 109,
	"ħ": 110,
	"ĩ": 111,
	"ī": 112,
	"ı": 113,
	"ķ": 114,
	"ĺ": 115,
	"ļ": 116,
	"ľ": 117,
	"ł": 118,
	"ń": 119,
	"ņ": 120,
	"ň": 121,
	"ō": 122,
	"ŏ": 123,
	"ő": 124,
	"œ": 125,
	"ř": 126,
	"ś": 127,
	"ş": 128,
	"š": 129,
	"ţ": 130,
	"ť": 131,
	"ũ": 132,
	"ū": 133,
	"ů": 134,
	"ų": 135,
	"ź": 136,
	"ż": 137,
	"ž": 138,
	"ơ": 139,
	"ư": 140,
	"ǀ": 141,
	"ǃ": 142,
	"ǎ": 143,
	"ǔ": 144,
	"ǫ": 145,
	"ǹ": 146,
	"ș": 147,
	"ț": 148,
	"ə": 149,
	"ɨ": 150,
	"ʉ": 151,
	"ʔ": 152,
	"ʻ": 153,
	"ʼ": 154,
	"ʽ": 155,
	"ʾ": 156,
	"ʿ": 157,
	"ː": 158,
	"ˢ": 159,
	"̀": 160,
	"́": 161,
	"̂": 162,
	"̃": 163,
	"̇": 164,
	"̈": 165,
	"̐": 166,
	"̠": 167,
	"̧": 168,
	"̱": 169,
	"̲": 170,
	"α": 171,
	"β": 172,
	"γ": 173,
	"δ": 174,
	"ε": 175,
	"ζ": 176,
	"η": 177,
	"θ": 178,
	"ι": 179,
	"κ": 180,
	"μ": 181,
	"ν": 182,
	"ο": 183,
	"π": 184,
	"ρ": 185,
	"ς": 186,
	"σ": 187,
	"τ": 188,
	"υ": 189,
	"ψ": 190,
	"ω": 191,
	"ό": 192,
	"а": 193,
	"г": 194,
	"е": 195,
	"з": 196,
	"и": 197,
	"к": 198,
	"м": 199,
	"н": 200,
	"п": 201,
	"р": 202,
	"э": 203,
	"я": 204,
	"і": 205,
	"ј": 206,
	"ҫ": 207,
	"գ": 208,
	"զ": 209,
	"ا": 210,
	"ب": 211,
	"ة": 212,
	"د": 213,
	"ر": 214,
	"ل": 215,
	"م": 216,
	"ن": 217,
	"و": 218,
	"ي": 219,
	"ቀ": 220,
	"ወ": 221,
	"ደ": 222,
	"ጠ": 223,
	"ḍ": 224,
	"ṅ": 225,
	"ṇ": 226,
	"ṣ": 227,
	"ṭ": 228,
	"ṯ": 229,
	"ạ": 230,
	"ả": 231,
	"ầ": 232,
	"ậ": 233,
	"ắ": 234,
	"ẵ": 235,
	"ề": 236,
	"ễ": 237,
	"ệ": 238,
	"ị": 239,
	"ồ": 240,
	"ổ": 241,
	"ộ": 242,
	"ờ": 243,
	"ợ": 244,
	"ủ": 245,
	"ử": 246,
	"ỳ": 247,
	"‐": 248,
	"–": 249,
	"—": 250,
	"―": 251,
	"‘": 252,
	"’": 253,
	"“": 254,
	"”": 255,
	"„": 256,
	"†": 257,
	"…": 258,
	"′": 259,
	"‹": 260,
	"›": 261,
	"€": 262,
	"₽": 263,
	"ℂ": 264,
	"ℕ": 265,
	"ℝ": 266,
	"ℤ": 267,
	"ℰ": 268,
	"ℵ": 269,
	"→": 270,
	"∅": 271,
	"∆": 272,
	"∈": 273,
	"−": 274,
	"∞": 275,
	"∨": 276,
	"∼": 277,
	"≥": 278,
	"─": 279,
	"☉": 280,
	"い": 281,
	"う": 282,
	"た": 283,
	"つ": 284,
	"ぬ": 285,
	"の": 286,
	"ひ": 287,
	"へ": 288,
	"ま": 289,
	"め": 290,
	"や": 291,
	"ゔ": 292,
	"乃": 293,
	"京": 294,
	"北": 295,
	"扬": 296,
	"文": 297,
	"星": 298,
	"术": 299,
	"杜": 300,
	"甌": 301,
	"美": 302,
	"西": 303,
	"貴": 304,
	"青": 305,
	"馆": 306,
	"ꝑ": 307,
	"고": 308,
	"기": 309,
	"먹": 310,
	"삼": 311,
	"생": 312,
	"집": 313
	}