add tokenizer

vocab.json

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