jz703's picture
Upload tokenizer
f1f7ac9
raw
history blame
1.23 kB
{
"</s>": 117,
"<s>": 116,
"[PAD]": 119,
"[UNK]": 118,
"aɪ": 15,
"aɪə": 4,
"aɪɚ": 79,
"aʊ": 75,
"dʒ": 25,
"eɪ": 113,
"iə": 72,
"iː": 36,
"n̩": 2,
"oʊ": 106,
"oː": 81,
"oːɹ": 57,
"tʃ": 84,
"uː": 82,
"ɑː": 114,
"ɑːɹ": 69,
"ɔɪ": 48,
"ɔː": 47,
"ɔːɹ": 71,
"əl": 80,
"ɛɹ": 107,
"ɜː": 95,
"ɪɹ": 65,
"ʊɹ": 54,
"ˈaɪ": 14,
"ˈaɪə": 99,
"ˈaɪɚ": 12,
"ˈaʊ": 38,
"ˈeɪ": 52,
"ˈiə": 53,
"ˈiː": 63,
"ˈoʊ": 11,
"ˈoː": 66,
"ˈoːɹ": 24,
"ˈuː": 115,
"ˈæ": 21,
"ˈɑː": 98,
"ˈɑːɹ": 74,
"ˈɔ": 56,
"ˈɔɪ": 91,
"ˈɔː": 108,
"ˈɔːɹ": 105,
"ˈɚ": 90,
"ˈɛ": 31,
"ˈɛɹ": 22,
"ˈɜː": 89,
"ˈɪ": 45,
"ˈɪɹ": 3,
"ˈʊ": 102,
"ˈʊɹ": 49,
"ˈʌ": 23,
"ˌaɪ": 33,
"ˌaɪɚ": 94,
"ˌaʊ": 111,
"ˌeɪ": 8,
"ˌiə": 19,
"ˌiː": 13,
"ˌn̩": 35,
"ˌoʊ": 58,
"ˌoː": 40,
"ˌoːɹ": 6,
"ˌuː": 39,
"ˌæ": 97,
"ˌɐ": 61,
"ˌɑː": 44,
"ˌɑːɹ": 93,
"ˌɔ": 18,
"ˌɔɪ": 10,
"ˌɔː": 70,
"ˌɔːɹ": 100,
"ˌɛ": 86,
"ˌɛɹ": 60,
"ˌɜː": 64,
"ˌɪ": 20,
"ˌɪɹ": 26,
"ˌʊ": 34,
"ˌʊɹ": 101,
"ˌʌ": 88
}