patrickvonplaten's picture
add tokenizer
541f0c1
{"b": 0, "t": 1, "n": 2, "l": 3, "z": 4, "h": 5, "i": 7, "e": 8, "o": 9, "k": 10, "j": 11, "ü": 12, "m": 13, "c": 14, "ğ": 15, "ç": 16, "u": 17, "ı": 18, "ş": 19, "y": 20, "s": 21, "a": 22, "g": 23, "d": 24, "ö": 25, "p": 26, "r": 27, "f": 28, "x": 29, "̇": 30, "v": 31, "'": 32, "â": 33, "|": 6, "[UNK]": 34, "[PAD]": 35}