Update app.py

app.py

@@ -93,11 +93,11 @@ def process_audio(audio):
 
 def generate_response(image, audio, text, count):
     count = int(count)
-    
+    overall_input = ""
     if audio:
-        text_from_audio = process_audio(audio)
+        overall_input = process_audio(audio)
     if text:
-        overall_input = text + text_from_audio
+        overall_input = text + overall_input
     if image:
         img_tokens = process_image(image)
         overall_input = "Question: " + overall_input + "Answer:"