scasutt's picture
add tokenizer
ca08f76
{"o": 0, "ö": 1, "f": 2, "e": 3, "ä": 4, "q": 5, "n": 6, "l": 7, "k": 8, "r": 9, "d": 10, "m": 11, "w": 12, "ü": 14, "j": 15, "i": 16, "x": 17, "g": 18, "t": 19, "p": 20, "s": 21, "h": 22, "c": 23, "u": 24, "v": 25, "a": 26, "z": 27, "b": 28, "y": 29, "|": 13, "[UNK]": 30, "[PAD]": 31}