add tokenizer

vocab.json

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