add tokenizer

vocab.json

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