add tokenizer

vocab.json

@@ -1 +1 @@
-{"o": 0, "m": 1, "e": 2, "j": 3, "z": 4, "f": 5, "'": 6, "k": 7, "c": 8, "p": 9, "r": 10, "n": 11, "d": 12, "i": 13, "w": 14, "x": 15, "g": 16, "v": 17, "a": 19, "s": 20, "y": 21, "q": 22, "t": 23, "u": 24, "b": 25, "h": 26, "l": 27, "|": 18, "[UNK]": 28, "[PAD]": 29}
+{"1": 0, "4": 1, "x": 2, "à": 3, "â": 4, "c": 5, "e": 6, "o": 7, "5": 8, "v": 9, "m": 10, "ç": 11, "n": 12, "w": 13, "h": 14, "ê": 15, "b": 16, "d": 17, "0": 18, "8": 19, "ü": 20, "3": 21, "j": 22, "g": 23, "k": 24, "t": 25, "u": 26, "y": 27, "a": 28, "è": 29, "ö": 30, "7": 31, "f": 32, "r": 33, "9": 34, "ä": 35, "z": 36, "2": 37, "é": 39, "s": 40, "i": 41, "q": 42, "6": 43, "p": 44, "l": 45, "|": 38, "[UNK]": 46, "[PAD]": 47}