HIYACCENT_Wav2Vec2 / vocab.json
codeceejay's picture
add tokenizer
e32aa20
raw
history blame contribute delete
No virus
268 Bytes
{"c": 0, "r": 2, "z": 3, "x": 4, "v": 5, "q": 6, "d": 7, "j": 8, "h": 9, "b": 10, "s": 11, "t": 12, "m": 13, "n": 14, "l": 15, "w": 16, "o": 17, "f": 18, "i": 19, "k": 20, "y": 21, "'": 22, "a": 23, "e": 24, "p": 25, "u": 26, "g": 27, "|": 1, "[UNK]": 28, "[PAD]": 29}