mms-tts-bsc / vocab.json
sanchit-gandhi's picture
Upload tokenizer
b98eb07
raw
history blame
388 Bytes
{
" ": 13,
"-": 6,
"_": 29,
"a": 10,
"b": 24,
"c": 11,
"d": 28,
"e": 9,
"f": 15,
"g": 25,
"h": 19,
"i": 32,
"j": 27,
"k": 23,
"l": 1,
"m": 20,
"n": 31,
"o": 12,
"p": 16,
"r": 30,
"s": 34,
"t": 21,
"u": 17,
"w": 7,
"x": 22,
"y": 26,
"ë": 5,
"ñ": 0,
"ŋ": 4,
"ŝ": 33,
"ƴ": 14,
"ɓ": 8,
"ɗ": 3,
"̃": 2,
"ỹ": 18
}