add tokenizer

vocab.json

@@ -1 +1 @@
-{"l": 0, "o": 1, "b": 2, "j": 3, "h": 4, "?": 5, "c": 6, ".": 7, "p": 8, "u": 9, "v": 11, "i": 12, "e": 13, "a": 14, "m": 15, "r": 16, "q": 17, "n": 18, "f": 19, "k": 20, "w": 21, "t": 22, "d": 23, "g": 24, "z": 25, "'": 26, "y": 27, "s": 28, "x": 29, "|": 10, "[UNK]": 30, "[PAD]": 31}
+{"l": 0, "o": 1, "b": 2, "j": 3, "h": 4, "c": 5, ".": 6, "p": 7, "u": 8, "v": 10, "i": 11, "e": 12, "a": 13, "m": 14, "r": 15, "q": 16, "n": 17, "f": 18, "k": 19, "w": 20, "t": 21, "d": 22, "g": 23, "z": 24, "'": 25, "y": 26, "s": 27, "x": 28, "|": 9, "[UNK]": 31, "[PAD]": 31}