add tokenizer

vocab.json

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