add tokenizer

vocab.json

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