add tokenizer

vocab.json

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