add tokenizer

vocab.json

@@ -1 +1 @@
-{"w": 0, "h": 1, "n": 2, "g": 3, "u": 4, "a": 5, "f": 6, "x": 7, "o": 8, "v": 9, "t": 10, "d": 11, "p": 12, "i": 13, "r": 14, "k": 15, "e": 16, "l": 17, "y": 18, "s": 19, "c": 21, "m": 22, "b": 23, "|": 20, "[UNK]": 24, "[PAD]": 25}
+{"a": 0, "p": 1, "w": 2, "k": 3, "h": 4, "n": 6, "g": 7, "e": 8, "s": 9, "l": 10, "r": 11, "y": 12, "c": 13, "d": 14, "b": 15, "v": 16, "u": 17, "f": 18, "m": 19, "t": 20, "i": 21, "x": 22, "o": 23, "|": 5, "[UNK]": 24, "[PAD]": 25}