mms-tts-hig / vocab.json
sanchit-gandhi's picture
Upload tokenizer
f7405cd
raw
history blame
398 Bytes
{
" ": 35,
"'": 31,
"-": 24,
"a": 2,
"b": 16,
"c": 27,
"d": 17,
"e": 20,
"f": 26,
"g": 14,
"h": 12,
"i": 4,
"j": 21,
"k": 8,
"l": 10,
"m": 3,
"n": 5,
"o": 33,
"p": 25,
"r": 13,
"s": 11,
"t": 6,
"u": 18,
"v": 22,
"w": 7,
"y": 9,
"z": 19,
"|": 0,
"á": 15,
"í": 34,
"ú": 32,
"ɓ": 29,
"ɗ": 28,
"ə": 1,
"́": 23,
"—": 30
}