add tokenizer

vocab.json

@@ -1 +1 @@
-{"#": 0, "o": 1, "4": 2, "/": 3, "e": 5, "a": 6, "u": 7, "'": 8, "y": 9, "j": 10, "_": 11, "8": 12, "n": 13, "v": 14, "r": 15, "3": 16, "c": 17, "k": 18, "0": 19, "t": 20, "q": 21, "%": 22, "z": 23, "s": 24, "l": 25, "1": 26, "m": 27, "h": 28, "f": 29, "d": 30, "6": 31, "b": 32, "g": 33, "x": 34, "2": 35, "i": 36, "w": 37, "5": 38, "p": 39, "|": 4, "[UNK]": 40, "[PAD]": 41}
+{"y": 0, "r": 1, "v": 2, "t": 3, "%": 4, "3": 5, "e": 6, "o": 7, "z": 8, "x": 9, "5": 10, "n": 11, "q": 12, "w": 13, "i": 14, "6": 15, "m": 16, "2": 17, "'": 18, "b": 19, "_": 20, "/": 21, "h": 22, "k": 23, "g": 24, "l": 25, "u": 26, "a": 27, "f": 28, "j": 29, "s": 31, "#": 32, "d": 33, "1": 34, "p": 35, "c": 36, "8": 37, "0": 38, "4": 39, "|": 30, "[UNK]": 40, "[PAD]": 41}