add tokenizer

vocab.json

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