add tokenizer

vocab.json

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