add tokenizer

vocab.json

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