add tokenizer

vocab.json

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