add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 44, "</s>": 45}
+{"<s>": 45, "</s>": 46}

vocab.json

@@ -1 +1 @@
-{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "à": 27, "á": 28, "ç": 29, "è": 30, "é": 31, "ê": 32, "ë": 33, "í": 34, "î": 35, "ï": 36, "ó": 37, "ö": 38, "ú": 39, "û": 40, "ü": 41, "|": 0, "[UNK]": 42, "[PAD]": 43}
+{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "à": 27, "á": 28, "ä": 29, "è": 30, "é": 31, "ê": 32, "ë": 33, "í": 34, "ï": 35, "ó": 36, "ö": 37, "ú": 38, "ü": 39, "ă": 40, "š": 41, "ţ": 42, "|": 0, "[UNK]": 43, "[PAD]": 44}