add tokenizer

vocab.json

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