add tokenizer

vocab.json

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