add tokenizer

vocab.json

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