add tokenizer

vocab.json

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