add tokenizer

vocab.json

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