xlsr-clp-nmcpc / vocab.json
susmitabhatt's picture
Upload tokenizer
d492e64 verified
raw
history blame
No virus
309 Bytes
{
"[PAD]": 27,
"[UNK]": 26,
"a": 6,
"b": 10,
"c": 13,
"d": 19,
"e": 21,
"f": 7,
"g": 17,
"h": 12,
"i": 15,
"j": 24,
"k": 11,
"l": 20,
"m": 1,
"n": 4,
"o": 9,
"p": 5,
"r": 2,
"s": 23,
"t": 0,
"u": 8,
"v": 22,
"w": 16,
"x": 25,
"y": 3,
"z": 18,
"|": 14
}