mms-tts-mgo / vocab.json
sanchit-gandhi's picture
Upload tokenizer
9475804
raw
history blame contribute delete
577 Bytes
{
" ": 29,
"'": 44,
"-": 36,
"_": 38,
"a": 30,
"b": 37,
"c": 13,
"d": 34,
"e": 31,
"f": 19,
"g": 7,
"h": 2,
"i": 35,
"j": 40,
"k": 20,
"l": 0,
"m": 8,
"n": 4,
"o": 42,
"p": 43,
"r": 32,
"s": 47,
"t": 50,
"u": 16,
"v": 17,
"w": 49,
"y": 33,
"z": 21,
"à": 26,
"â": 27,
"è": 45,
"ê": 28,
"ì": 12,
"î": 46,
"ò": 10,
"ô": 14,
"ù": 18,
"û": 41,
"ě": 5,
"ŋ": 6,
"ǎ": 25,
"ǐ": 3,
"ǒ": 9,
"ǔ": 15,
"ɔ": 48,
"ə": 22,
"ɨ": 24,
"ʼ": 1,
"̀": 11,
"̂": 23,
"̌": 39
}