add tokenizer

vocab.json

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