add tokenizer

vocab.json

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