mms-1b-l1107-nan / vocab.json
d9021001's picture
Upload tokenizer
93ba61c
raw
history blame
697 Bytes
{
"nan": {
"[PAD]": 49,
"[UNK]": 48,
"a": 1,
"b": 2,
"c": 3,
"e": 4,
"g": 5,
"h": 6,
"i": 7,
"j": 8,
"k": 9,
"l": 10,
"m": 11,
"n": 12,
"o": 13,
"p": 14,
"r": 15,
"s": 16,
"t": 17,
"u": 18,
"y": 19,
"|": 0,
"à": 21,
"á": 22,
"è": 23,
"é": 24,
"ê": 25,
"ì": 26,
"í": 27,
"ò": 28,
"ó": 29,
"ù": 30,
"ú": 31,
"ā": 32,
"ē": 33,
"ī": 34,
"ı": 35,
"ń": 36,
"ō": 37,
"ū": 38,
"ǎ": 39,
"ǹ": 40,
"́": 41,
"̂": 42,
"̄": 43,
"̍": 44,
"͘": 45,
"ḿ": 46,
"ⁿ": 47,
"⿸": 48
}
}