add tokenizer

vocab.json

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