add tokenizer

vocab.json

@@ -1 +1 @@
-{"n": 0, "i": 1, "c": 2, "p": 3, "b": 4, "a": 5, "t": 6, "h": 7, "y": 8, "o": 9, "w": 10, "e": 11, "d": 12, "k": 13, "x": 14, "l": 16, "m": 17, "f": 18, "s": 19, "r": 20, "v": 21, "u": 22, "g": 23, "|": 15, "[UNK]": 24, "[PAD]": 25}
+{"o": 0, "p": 1, "k": 2, "w": 3, "f": 4, "l": 5, "r": 6, "s": 7, "e": 8, "y": 9, "a": 10, "u": 11, "c": 12, "t": 13, "n": 14, "x": 15, "v": 16, "b": 17, "i": 18, "h": 19, "g": 20, "m": 22, "d": 23, "|": 21, "[UNK]": 24, "[PAD]": 25}