Update app.py

app.py

@@ -189,8 +189,10 @@ text_mc_tokenizer = AutoTokenizer.from_pretrained(text_mc_model_path)
 text_mc_model = AutoModelForSequenceClassification.from_pretrained(text_mc_model_path).to(device)
 
 def remove_special_characters(text):
-    cleaned_text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
-    return cleaned_text
+    text = remove_accents(text)
+    pattern = r'[^\w\s\d.,!?\'"()-;]+'
+    text = re.sub(pattern, '', text)
+    return text
 
 def update_character_count(text):
     return f"{len(text)} characters"