wav2vec2-colab / vocab.json
Nithiwat's picture
Upload tokenizer
34dc7a8
raw
history blame
496 Bytes
{
"[PAD]": 40,
"[UNK]": 39,
"a": 0,
"aː": 1,
"b": 2,
"d": 3,
"e": 4,
"eː": 5,
"f": 6,
"h": 7,
"i": 8,
"iː": 9,
"j": 10,
"k": 11,
"kʰ": 12,
"l": 13,
"m": 14,
"n": 15,
"o": 16,
"oː": 17,
"p": 18,
"pʰ": 19,
"r": 20,
"s": 21,
"t": 22,
"tʰ": 23,
"t͡ɕ": 24,
"t͡ɕʰ": 25,
"u": 26,
"uː": 27,
"w": 28,
"ŋ": 29,
"ɔ": 30,
"ɔː": 31,
"ɛ": 32,
"ɛː": 33,
"ɤ": 34,
"ɤː": 35,
"ɯ": 36,
"ɯː": 37,
"ʔ": 38
}