add tokenizer

vocab.json

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