add tokenizer

vocab.json

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