add tokenizer

vocab.json

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