mms-tts-lee / vocab.json
sanchit-gandhi's picture
Upload tokenizer
5c604c3
raw
history blame contribute delete
736 Bytes
{
" ": 63,
"'": 24,
"-": 36,
"a": 13,
"b": 7,
"c": 22,
"d": 14,
"e": 32,
"f": 52,
"g": 27,
"h": 20,
"i": 15,
"j": 37,
"k": 21,
"l": 10,
"m": 9,
"n": 2,
"o": 53,
"p": 38,
"r": 12,
"s": 19,
"t": 23,
"u": 35,
"v": 48,
"w": 8,
"y": 5,
"z": 17,
"|": 0,
"à": 18,
"á": 16,
"â": 49,
"ã": 46,
"è": 42,
"é": 28,
"ê": 45,
"ì": 26,
"í": 25,
"ò": 39,
"ó": 33,
"ô": 58,
"õ": 54,
"ù": 34,
"ú": 40,
"ě": 56,
"ĩ": 50,
"ń": 29,
"ŋ": 51,
"ũ": 57,
"ǎ": 44,
"ǐ": 47,
"ǒ": 59,
"ǔ": 55,
"ǹ": 30,
"ɔ": 11,
"ə": 1,
"ɛ": 6,
"̀": 4,
"́": 3,
"̂": 62,
"̃": 31,
"̌": 41,
"ṍ": 61,
"ṹ": 60,
"ẽ": 43
}