Transformers
sip-fst-tokenizer / tokenizer.json
namednil's picture
Upload tokenizer
ba3216f verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "."
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[PAD]": 0,
"'": 1,
"ɕ": 2,
"ɘ": 3,
"ɝ": 4,
"ɸ": 5,
"ɹ": 6,
"ɾ": 7,
"ʁ": 8,
"ʎ": 9,
"ʏ": 10,
"ʔ": 11,
"A": 12,
"B": 13,
"C": 14,
"D": 15,
"E": 16,
"F": 17,
"G": 18,
"H": 19,
"I": 20,
"J": 21,
"K": 22,
"L": 23,
"M": 24,
"N": 25,
"O": 26,
"P": 27,
"Q": 28,
"R": 29,
"S": 30,
"T": 31,
"U": 32,
"V": 33,
"W": 34,
"X": 35,
"Y": 36,
"Z": 37,
"a": 38,
"b": 39,
"c": 40,
"d": 41,
"e": 42,
"f": 43,
"g": 44,
"h": 45,
"i": 46,
"j": 47,
"k": 48,
"l": 49,
"m": 50,
"n": 51,
"o": 52,
"p": 53,
"q": 54,
"r": 55,
"s": 56,
"t": 57,
"u": 58,
"v": 59,
"w": 60,
"x": 61,
"y": 62,
"z": 63,
"«": 64,
"»": 65,
"ɐ": 66,
"ɑ": 67,
"ɒ": 68,
"ɔ": 69,
"ə": 70,
"ɛ": 71,
"ɜ": 72,
"ɡ": 73,
"ɦ": 74,
"ɪ": 75,
"ɱ": 76,
"ɲ": 77,
"ʀ": 78,
"ʃ": 79,
"ʊ": 80,
"ʋ": 81,
"ʌ": 82,
"ʒ": 83,
"ʰ": 84,
"ʲ": 85,
"ʼ": 86,
"ˀ": 87,
"˂": 88,
"˃": 89,
"ː": 90,
"ˑ": 91,
"˵": 92,
"˶": 93,
"˹": 94,
"˺": 95,
"̃": 96,
"̆": 97,
"̊": 98,
"̍": 99,
"̝": 100,
"̞": 101,
"̥": 102,
"̩": 103,
"̪": 104,
"̯": 105,
"͜": 106,
"͡": 107,
"‴": 108,
"‷": 109,
"‿": 110,
"⁽": 111,
"⁾": 112,
"\t": 113,
"\n": 114,
"\u000b": 115,
"\f": 116,
"\r": 117,
"\u000e": 118,
"\u000f": 119,
"\u0010": 120,
"\u0011": 121,
"\u0012": 122,
"\u0013": 123,
"\u0014": 124,
"\u0015": 125,
"\u0016": 126,
"\u0017": 127,
"\u0018": 128,
"\u0019": 129,
"\u001a": 130,
"\u001b": 131,
"\u001c": 132,
"\u001d": 133,
"\u001e": 134,
"\u001f": 135,
" ": 136,
"!": 137,
"\"": 138,
"#": 139,
"$": 140,
"%": 141,
"&": 142,
"(": 143,
")": 144,
"*": 145,
"+": 146,
",": 147,
"-": 148,
".": 149,
"/": 150,
"0": 151,
"1": 152,
"2": 153,
"3": 154,
"4": 155,
"5": 156,
"6": 157,
"7": 158,
"8": 159,
"9": 160,
":": 161,
";": 162,
"<": 163,
"=": 164,
">": 165,
"?": 166,
"@": 167,
"[": 168,
"\\": 169,
"]": 170,
"^": 171,
"_": 172,
"`": 173,
"{": 174,
"|": 175,
"}": 176,
"~": 177,
"": 178,
"À": 179,
"Á": 180,
"Ã": 181,
"Ä": 182,
"Æ": 183,
"Ç": 184,
"È": 185,
"É": 186,
"Ê": 187,
"Ë": 188,
"Í": 189,
"Ó": 190,
"Õ": 191,
"Ö": 192,
"Ø": 193,
"Ü": 194,
"ß": 195,
"à": 196,
"á": 197,
"ã": 198,
"ä": 199,
"æ": 200,
"ç": 201,
"è": 202,
"é": 203,
"ê": 204,
"ë": 205,
"í": 206,
"ó": 207,
"õ": 208,
"ö": 209,
"ø": 210,
"ü": 211,
"Ġ": 212,
"ġ": 213,
"Ŋ": 214,
"ŋ": 215,
"Œ": 216,
"œ": 217,
"Ɔ": 218,
"Ə": 219,
"Ɛ": 220,
"Ɲ": 221,
"Ʀ": 222,
"Ʃ": 223,
"Ʊ": 224,
"Ʋ": 225,
"Ʒ": 226,
"Ʌ": 227,
"ɓ": 228,
"ɖ": 229,
"ɗ": 230,
"ɚ": 231,
"ɞ": 232,
"ɟ": 233,
"ɠ": 234,
"ɢ": 235,
"ɣ": 236,
"ɤ": 237,
"ɥ": 238,
"ɧ": 239,
"ɨ": 240,
"ɩ": 241,
"ɫ": 242,
"ɬ": 243,
"ɭ": 244,
"ɮ": 245,
"ɯ": 246,
"ɰ": 247,
"ɳ": 248,
"ɴ": 249,
"ɵ": 250,
"ɶ": 251,
"ɷ": 252,
"ɺ": 253,
"ɻ": 254,
"ɼ": 255,
"ɽ": 256,
"ɿ": 257,
"ʂ": 258,
"ʄ": 259,
"ʅ": 260,
"ʆ": 261,
"ʇ": 262,
"ʈ": 263,
"ʉ": 264,
"ʍ": 265,
"ʐ": 266,
"ʑ": 267,
"ʓ": 268,
"ʕ": 269,
"ʖ": 270,
"ʗ": 271,
"ʘ": 272,
"ʙ": 273,
"ʚ": 274,
"ʛ": 275,
"ʜ": 276,
"ʝ": 277,
"ʞ": 278,
"ʟ": 279,
"ʠ": 280,
"ʡ": 281,
"ʢ": 282,
"ʣ": 283,
"ʤ": 284,
"ʥ": 285,
"ʦ": 286,
"ʧ": 287,
"ʨ": 288,
"ʩ": 289,
"ʪ": 290,
"ʫ": 291,
"ʬ": 292,
"ʭ": 293,
"ʮ": 294,
"ʯ": 295,
"Θ": 296,
"Χ": 297,
"θ": 298,
"χ": 299,
"Ɑ": 300,
"Ɱ": 301,
"Ɐ": 302,
"Ɒ": 303,
"Ɦ": 304,
"Ɜ": 305,
"Ɡ": 306,
"Ɪ": 307
},
"unk_token": "[UNK]"
}
}