add tokenizer

vocab.json

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