add tokenizer

vocab.json

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