Ubuntu

adding saved tokenizer

462fb62 about 3 years ago

No virus

236 Bytes

{"k": 0, "p": 1, "d": 2, "o": 3, "h": 4, "m": 6, "ɛ": 7, "ɔ": 8, "n": 9, "’": 10, "g": 11, "b": 12, "t": 13, "s": 14, "r": 15, "u": 16, "l": 17, "e": 18, "w": 19, "a": 20, "f": 21, "y": 22, "i": 23, "|": 5, "[UNK]": 24, "[PAD]": 25}