add tokenizer

vocab.json

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