add tokenizer

vocab.json

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