add tokenizer

vocab.json

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