xlsr-big-kannn / vocab.json
susmitabhatt's picture
Upload tokenizer
cf0a264 verified
raw
history blame
No virus
298 Bytes
{
"D": 20,
"O": 19,
"T": 21,
"[PAD]": 26,
"[UNK]": 25,
"a": 0,
"b": 4,
"c": 3,
"d": 15,
"e": 5,
"g": 8,
"h": 17,
"i": 11,
"j": 23,
"k": 16,
"l": 18,
"m": 12,
"n": 22,
"o": 1,
"p": 2,
"r": 14,
"s": 7,
"t": 9,
"u": 24,
"v": 6,
"y": 13,
"|": 10
}