add tokenizer

vocab.json

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