add tokenizer

vocab.json

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