add tokenizer

vocab.json

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