mms-tts-cme / vocab.json
sanchit-gandhi's picture
Upload tokenizer
350d0ac
raw
history blame
400 Bytes
{
" ": 35,
"'": 32,
"-": 12,
"a": 1,
"b": 7,
"c": 24,
"d": 13,
"e": 8,
"f": 26,
"g": 20,
"h": 23,
"i": 2,
"j": 29,
"k": 18,
"l": 10,
"m": 6,
"n": 5,
"o": 9,
"p": 28,
"r": 16,
"s": 17,
"t": 21,
"u": 3,
"v": 33,
"w": 25,
"y": 15,
"|": 0,
"ã": 22,
"ĩ": 27,
"ŋ": 4,
"ũ": 30,
"ɔ": 11,
"ɛ": 14,
"̃": 31,
"‐": 19,
"—": 34
}