jz703's picture
Upload tokenizer
4ffcb2e
raw
history blame
937 Bytes
{
"[PAD]": 72,
"[UNK]": 71,
"aɪ": 8,
"aʊ": 63,
"b": 37,
"d": 15,
"d͡ʒ": 69,
"eɪ": 38,
"f": 51,
"h": 70,
"i": 61,
"j": 67,
"k": 2,
"l": 25,
"m": 29,
"n": 39,
"oʊ": 9,
"p": 23,
"s": 55,
"t": 49,
"t͡ʃ": 35,
"u": 16,
"v": 44,
"w": 12,
"z": 1,
"|": 0,
"æ": 27,
"ð": 18,
"ŋ": 54,
"ɑ": 60,
"ɔ": 30,
"ɔɪ": 28,
"ə": 7,
"ɚ": 47,
"ɛ": 58,
"ɡ": 3,
"ɪ": 56,
"ɹ": 40,
"ʃ": 68,
"ʊ": 6,
"ʌ": 10,
"ʒ": 43,
"ˈaɪ": 33,
"ˈaʊ": 26,
"ˈeɪ": 48,
"ˈi": 34,
"ˈoʊ": 62,
"ˈu": 50,
"ˈæ": 36,
"ˈɑ": 17,
"ˈɔ": 21,
"ˈɔɪ": 59,
"ˈɚ": 57,
"ˈɛ": 22,
"ˈɪ": 19,
"ˈʊ": 5,
"ˈʌ": 41,
"ˌaɪ": 13,
"ˌaʊ": 53,
"ˌeɪ": 45,
"ˌi": 24,
"ˌoʊ": 32,
"ˌu": 11,
"ˌæ": 42,
"ˌɑ": 14,
"ˌɔ": 66,
"ˌɔɪ": 65,
"ˌɚ": 31,
"ˌɛ": 20,
"ˌɪ": 52,
"ˌʊ": 4,
"ˌʌ": 46,
"θ": 64
}