add tokenizer

vocab.json

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