tokenizer_ipa_vocab / added_tokens.json
m.utrobin
tokenizer upload
21f6b53
{
" ": 104,
"'": 79,
"+": 60,
"+a": 29,
"+e": 28,
"+i": 10,
"+j": 11,
"+o": 21,
"+u": 9,
"+ɨ": 26,
".": 148,
"a": 132,
"b": 63,
"bʲ": 4,
"c": 98,
"d": 39,
"dʲ": 32,
"d͡ʒ": 24,
"e": 94,
"f": 136,
"fʲ": 15,
"g": 131,
"h": 159,
"i": 112,
"j": 170,
"k": 168,
"kʲ": 8,
"l": 138,
"lʲ": 25,
"m": 97,
"mʲ": 20,
"n": 110,
"nʲ": 18,
"o": 34,
"p": 108,
"pʲ": 14,
"q": 103,
"r": 141,
"rʲ": 23,
"s": 144,
"sʲ": 6,
"t": 84,
"tʲ": 16,
"t͡": 13,
"t͡s": 17,
"t͡ɕ": 22,
"t͡ʃ": 27,
"u": 70,
"v": 101,
"vʲ": 19,
"w": 96,
"x": 58,
"xʲ": 30,
"y": 56,
"z": 95,
"zʲ": 5,
"æ": 67,
"ç": 129,
"ð": 162,
"ø": 54,
"ħ": 61,
"ŋ": 35,
"œ": 143,
"ǀ": 125,
"ǁ": 68,
"ǂ": 166,
"ǃ": 89,
"ɐ": 107,
"ɑ": 137,
"ɒ": 164,
"ɓ": 169,
"ɔ": 57,
"ɕ": 49,
"ɕʲ": 31,
"ɖ": 145,
"ɗ": 154,
"ɘ": 158,
"ə": 45,
"ɚ": 72,
"ɛ": 109,
"ɜ": 62,
"ɝ": 92,
"ɞ": 46,
"ɟ": 65,
"ɠ": 50,
"ɡ": 33,
"ɢ": 126,
"ɣ": 122,
"ɤ": 119,
"ɥ": 99,
"ɦ": 117,
"ɧ": 77,
"ɨ": 76,
"ɪ": 42,
"ɫ": 87,
"ɬ": 71,
"ɭ": 142,
"ɮ": 74,
"ɯ": 140,
"ɰ": 149,
"ɱ": 128,
"ɲ": 81,
"ɳ": 85,
"ɴ": 102,
"ɵ": 44,
"ɶ": 59,
"ɸ": 115,
"ɹ": 78,
"ɺ": 130,
"ɻ": 123,
"ɽ": 160,
"ɾ": 157,
"ʀ": 88,
"ʁ": 93,
"ʂ": 55,
"ʂʲ": 7,
"ʃ": 153,
"ʄ": 165,
"ʈ": 156,
"ʈ͡ʂ": 12,
"ʉ": 80,
"ʊ": 139,
"ʋ": 161,
"ʌ": 40,
"ʍ": 83,
"ʎ": 106,
"ʏ": 86,
"ʐ": 120,
"ʑ": 66,
"ʒ": 36,
"ʔ": 135,
"ʕ": 75,
"ʘ": 113,
"ʙ": 111,
"ʛ": 51,
"ʜ": 127,
"ʝ": 100,
"ʟ": 114,
"ʡ": 38,
"ʢ": 105,
"ʤ": 152,
"ʧ": 146,
"ʰ": 64,
"ʱ": 121,
"ʲ": 150,
"ʴ": 155,
"ʷ": 69,
"ʼ": 151,
"ˈ": 52,
"ˌ": 90,
"ː": 118,
"ˑ": 134,
"˞": 91,
"ˠ": 147,
"ˤ": 41,
"̩": 48,
"͡": 116,
"β": 43,
"θ": 37,
"χ": 82,
"ᵻ": 124,
"↑": 167,
"→": 53,
"↓": 133,
"↗": 47,
"↘": 73,
"ⱱ": 163
}