add tokenizer

vocab.json

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