add tokenizer

vocab.json

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