Update app.py

app.py

@@ -293,7 +293,7 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
 def transcribe_and_predict_video(video, user_input, chat_history=[]):
     # Process the video for emotions (use your own emotion detection functions)
     image_emotion = process_video(video)
-    text_emotion, audio_emotion = process_audio_from_video(video)
+    text_emotion, audio_emotion,text = process_audio_from_video(video)
     em = [image_emotion, text_emotion, audio_emotion]
 
     # Format the conversation history
@@ -304,7 +304,7 @@ def transcribe_and_predict_video(video, user_input, chat_history=[]):
     You are a helpful AI assistant. Respond like a human while considering the user's emotion.
 
     User's Emotion: {em}
-
+    video text context: {text}
     Conversation History:
     {history_text}