add tokenizer

vocab.json

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