add tokenizer

vocab.json

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