add tokenizer

vocab.json

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