add tokenizer

vocab.json

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