xlsr-timit-c0 / vocab.json
arunasrivastava
tokenizer and config
7f03efa
raw
history blame contribute delete
474 Bytes
{
"</s>": 2,
"<s>": 1,
"[PAD]": 0,
"[UNK]": 3,
"a": 4,
"b": 5,
"d": 6,
"e": 7,
"f": 8,
"h": 9,
"i": 10,
"j": 11,
"k": 12,
"l": 13,
"m": 14,
"n": 15,
"o": 16,
"p": 17,
"s": 18,
"t": 19,
"u": 20,
"v": 21,
"w": 22,
"z": 23,
"æ": 24,
"ð": 25,
"ŋ": 26,
"ɑ": 27,
"ɔ": 28,
"ə": 29,
"ɛ": 30,
"ɡ": 31,
"ɪ": 32,
"ɹ": 33,
"ɾ": 34,
"ʃ": 35,
"ʊ": 36,
"ʌ": 37,
"ʒ": 38,
"ʔ": 39,
"θ": 40
}