add tokenizer

vocab.json

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