add tokenizer

vocab.json

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