xlsr-aiish-nose / vocab.json
susmitabhatt's picture
Upload tokenizer
bd44102 verified
raw
history blame
No virus
309 Bytes
{
"D": 20,
"K": 23,
"O": 15,
"T": 8,
"[PAD]": 27,
"[UNK]": 26,
"a": 2,
"b": 6,
"c": 24,
"d": 0,
"e": 9,
"g": 5,
"h": 12,
"i": 10,
"j": 1,
"k": 22,
"l": 4,
"m": 13,
"n": 16,
"o": 7,
"p": 19,
"r": 25,
"s": 18,
"t": 14,
"u": 3,
"v": 17,
"y": 11,
"|": 21
}