add tokenizer

vocab.json

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