add tokenizer

vocab.json

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