add tokenizer

vocab.json

@@ -1 +1 @@
-{"q": 0, "a": 1, "t": 2, "y": 3, "k": 4, "h": 5, "c": 6, "i": 7, "z": 8, "m": 9, "o": 10, "e": 11, "x": 12, "f": 13, "b": 14, "l": 15, "v": 16, "n": 18, "ü": 19, "d": 20, "p": 21, "j": 22, "ö": 23, "w": 24, "ä": 25, "s": 26, "r": 27, "g": 28, "u": 29, "|": 17, "[UNK]": 30, "[PAD]": 31}
+{"x": 0, "w": 1, "ä": 2, "t": 3, "k": 4, "i": 5, "o": 6, "ö": 7, "b": 8, "ü": 9, "q": 10, "s": 11, "f": 12, "m": 13, "n": 14, "e": 15, "z": 16, "g": 17, "v": 18, "u": 19, "c": 20, "d": 21, "h": 22, "a": 24, "l": 25, "y": 26, "p": 27, "r": 28, "j": 29, "|": 23, "[UNK]": 30, "[PAD]": 31}