add tokenizer

vocab.json

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