add tokenizer

vocab.json

@@ -1 +1 @@
-{"h": 0, "j": 1, "b": 2, "k": 3, "f": 4, "r": 5, "p": 6, "o": 7, "a": 8, "v": 9, "y": 10, "e": 11, "n": 13, "s": 14, "g": 15, "z": 16, "q": 17, "d": 18, "u": 19, "l": 20, "c": 21, "w": 23, "x": 24, "i": 25, "t": 26, "m": 27, "[UNK]": 28, "[PAD]": 29, "|": 22}
+{"a": 0, "v": 1, "x": 2, "c": 3, "r": 5, "z": 6, "t": 7, "j": 8, "f": 9, "g": 10, "h": 11, "o": 12, "m": 13, "i": 14, "p": 15, "b": 17, "y": 18, "l": 19, "u": 20, "w": 21, "q": 22, "e": 23, "n": 24, "k": 25, "d": 26, "s": 27, "[UNK]": 28, "[PAD]": 29, "|": 16}