add tokenizer

vocab.json

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