add tokenizer

vocab.json

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