add tokenizer

vocab.json

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