add tokenizer

vocab.json

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