add tokenizer

vocab.json

@@ -1 +1 @@
-{"h": 0, "v": 1, "y": 2, "l": 3, "ç": 4, "s": 5, "z": 6, "ô": 7, "o": 8, "e": 9, "í": 11, "ã": 12, "ú": 13, "p": 14, "r": 15, "a": 16, "k": 17, "q": 18, "x": 19, "m": 20, "j": 21, "ó": 22, "d": 23, "é": 24, "w": 25, "c": 26, "â": 27, "t": 28, "i": 29, "b": 30, "f": 31, "u": 32, "õ": 33, "n": 34, "á": 35, "g": 36, "ê": 37, "|": 10, "[UNK]": 38, "[PAD]": 39}
+{"á": 0, "g": 1, "x": 2, "ã": 3, "i": 4, "ô": 5, "l": 6, "t": 7, "ó": 8, "w": 9, "ç": 10, "r": 11, "v": 12, "s": 13, "h": 14, "í": 15, "z": 16, "d": 17, "b": 18, "ú": 19, "y": 20, "ê": 21, "a": 22, "c": 23, "k": 24, "e": 25, "q": 26, "é": 27, "â": 29, "õ": 30, "m": 31, "o": 32, "p": 33, "f": 34, "n": 35, "u": 36, "j": 37, "|": 28, "[UNK]": 38, "[PAD]": 39}