add tokenizer

vocab.json

@@ -1 +1 @@
-{"7": 0, "'": 1, "q": 2, "z": 3, "5": 4, "h": 5, "n": 6, "x": 7, "6": 8, "o": 9, "f": 10, "4": 11, "1": 12, "y": 13, "j": 14, "u": 15, "r": 16, "d": 17, "w": 18, "m": 19, "9": 20, "k": 21, "é": 22, "2": 23, "a": 24, "8": 25, "v": 26, "3": 28, "l": 29, "0": 30, "s": 31, "ñ": 32, "i": 33, "p": 34, "g": 35, "c": 36, "b": 37, "e": 38, "t": 39, "|": 27, "[UNK]": 40, "[PAD]": 41}
+{"'": 1, "a": 24, "b": 37, "c": 36, "d": 17, "e": 38, "f": 10, "g": 35, "h": 5, "i": 33, "j": 14, "k": 21, "l": 29, "m": 19, "n": 6, "o": 9, "p": 34, "q": 2, "r": 16, "s": 31, "t": 39, "u": 15, "v": 26, "w": 18, "x": 7, "y": 13, "z": 3, "|": 27, "[UNK]": 40, "[PAD]": 41}