add tokenizer

vocab.json

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