add tokenizer

vocab.json

@@ -1 +1 @@
-{"t": 0, "b": 1, "q": 2, "o": 3, "j": 4, "d": 5, "i": 6, "n": 7, "g": 8, "f": 9, "h": 10, "e": 11, "a": 12, "p": 13, "v": 14, "s": 16, "k": 17, "u": 18, "c": 19, "m": 20, "y": 21, "w": 22, "z": 23, "r": 24, "l": 25, "|": 15, "[UNK]": 26, "[PAD]": 27}
+{"w": 0, "z": 1, "e": 2, "o": 3, "h": 4, "q": 5, "i": 6, "l": 7, "g": 8, "t": 9, "j": 10, "r": 12, "d": 13, "p": 14, "u": 15, "v": 16, "s": 17, "c": 18, "y": 19, "a": 20, "m": 21, "b": 22, "n": 23, "k": 24, "f": 25, "|": 11, "[UNK]": 26, "[PAD]": 27}