add tokenizer

vocab.json

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