add tokenizer

vocab.json

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