add tokenizer

vocab.json

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