wav2vec2-kab / vocab.json
TifinLab's picture
Upload tokenizer
dd30dd7 verified
raw
history blame
605 Bytes
{
"-": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"5": 6,
"6": 7,
"7": 8,
"8": 9,
"9": 10,
"[PAD]": 52,
"[UNK]": 51,
"a": 11,
"b": 12,
"c": 13,
"d": 14,
"e": 15,
"f": 16,
"g": 17,
"h": 18,
"i": 19,
"j": 20,
"k": 21,
"l": 22,
"m": 23,
"n": 24,
"o": 25,
"p": 26,
"q": 27,
"r": 28,
"s": 29,
"t": 30,
"u": 31,
"v": 32,
"w": 33,
"x": 34,
"y": 35,
"z": 36,
"|": 0,
"ç": 37,
"č": 38,
"ǧ": 39,
"ɛ": 40,
"ɣ": 41,
"̣": 42,
"σ": 43,
"ḍ": 44,
"ḥ": 45,
"ṛ": 46,
"ṣ": 47,
"ṭ": 48,
"ẓ": 49,
"€": 50
}