add tokenizer

vocab.json

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