add tokenizer

vocab.json

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