STT_Model_18 / vocab.json
LowGI's picture
Upload tokenizer
bfdcdac
raw
history blame
331 Bytes
{
"'": 10,
"[PAD]": 29,
"[UNK]": 28,
"a": 8,
"b": 13,
"c": 1,
"d": 11,
"e": 4,
"f": 12,
"g": 24,
"h": 21,
"i": 14,
"j": 7,
"k": 15,
"l": 6,
"m": 26,
"n": 16,
"o": 18,
"p": 9,
"q": 2,
"r": 25,
"s": 27,
"t": 20,
"u": 5,
"v": 17,
"w": 3,
"x": 19,
"y": 23,
"z": 0,
"|": 22
}