XLS-R_timit_en / vocab.json
hadiqa123's picture
add tokenizer
edb4445
raw
history blame
268 Bytes
{"o": 0, "q": 1, "v": 2, "e": 3, "n": 4, "g": 5, "s": 6, "h": 7, "f": 8, "x": 9, "i": 10, "y": 11, "c": 12, "w": 13, "z": 15, "u": 16, "j": 17, "d": 18, "k": 19, "b": 20, "m": 21, "a": 22, "p": 23, "t": 24, "r": 25, "l": 26, "'": 27, "|": 14, "[UNK]": 28, "[PAD]": 29}