mHuBERT-147-br / vocab.json
gweltou's picture
Upload tokenizer
3f56d20 verified
raw
history blame
No virus
546 Bytes
{
"'": 24,
"3": 37,
"[PAD]": 47,
"[UNK]": 46,
"a": 33,
"b": 17,
"c": 12,
"d": 4,
"e": 11,
"f": 34,
"g": 9,
"h": 42,
"i": 31,
"j": 6,
"k": 44,
"l": 14,
"m": 27,
"n": 2,
"o": 23,
"p": 35,
"q": 3,
"r": 7,
"s": 18,
"t": 13,
"u": 16,
"v": 28,
"w": 15,
"x": 43,
"y": 0,
"z": 26,
"|": 8,
"à": 21,
"á": 5,
"â": 20,
"ã": 22,
"ç": 41,
"è": 32,
"é": 36,
"ê": 25,
"ë": 40,
"ñ": 29,
"ô": 19,
"ö": 10,
"ø": 30,
"ù": 1,
"û": 45,
"ü": 38,
"ı": 39
}