add tokenizer

vocab.json

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