add tokenizer

vocab.json

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