add tokenizer

vocab.json

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