add tokenizer

vocab.json

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