add tokenizer

vocab.json

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