wav2vec2-colab / vocab.json
Nithiwat's picture
add tokenizer
85dd337
raw
history blame
400 Bytes
{"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, "t͡ɕ": 23, "t͡ɕʰ": 24, "u": 25, "uː": 26, "w": 27, "ŋ": 28, "ɔ": 29, "ɔː": 30, "ɛ": 31, "ɛː": 32, "ɤ": 33, "ɤː": 34, "ɯ": 35, "ɯː": 36, "ʔ": 37, "[UNK]": 38, "[PAD]": 39}