mms-tts-jbu / vocab.json
sanchit-gandhi's picture
Upload tokenizer
3461794
raw
history blame contribute delete
541 Bytes
{
" ": 47,
"'": 26,
"-": 40,
"a": 1,
"b": 5,
"c": 16,
"d": 8,
"e": 7,
"f": 21,
"g": 22,
"h": 20,
"i": 3,
"j": 17,
"k": 6,
"l": 28,
"m": 14,
"n": 2,
"o": 11,
"p": 19,
"q": 45,
"r": 12,
"s": 13,
"t": 15,
"u": 4,
"v": 24,
"w": 9,
"y": 10,
"z": 18,
"|": 0,
"­": 25,
"à": 23,
"á": 31,
"â": 46,
"è": 35,
"é": 37,
"ì": 36,
"í": 27,
"ò": 30,
"ó": 42,
"ù": 34,
"ú": 32,
"ā": 33,
"ē": 39,
"ī": 29,
"ō": 38,
"ū": 44,
"̀": 41,
"ḿ": 43
}