Update app.py

app.py

@@ -2,11 +2,11 @@ import streamlit as st
 import os
 import cv2
 import torch
-import moviepy.editor as mp
+
 from PIL import Image
 from gtts import gTTS
 from scenedetect import open_video, SceneManager, ContentDetector
-from transformers import BlipProcessor, BlipForConditionalGeneration, AutoModelForCausalLM, AutoTokenizer
+from transformers import BlipProcessor, BlipForConditionalGeneration
 from openai import OpenAI
 # Load AI models
 caption_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
@@ -97,18 +97,19 @@ if uploaded_file:
         tts.save(output_audio)
     
     text_to_speech(summary)
+    st.audio('summary_audio.mp3')
 
-    # Combine Audio & Video
-    st.write("🎬 Merging audio with the video...")
+    # # Combine Audio & Video
+    # st.write("🎬 Merging audio with the video...")
 
-    def add_audio_to_video(video_path, audio_path, output_video="final_video.mp4"):
-        video = mp.VideoFileClip(video_path)
-        audio = mp.AudioFileClip(audio_path)
-        if audio.duration > video.duration:
-            audio = audio.subclip(0, video.duration)
-        final_video = video.set_audio(audio)
-        final_video.write_videofile(output_video, codec="libx264", audio_codec="aac")
+    # def add_audio_to_video(video_path, audio_path, output_video="final_video.mp4"):
+    #     video = mp.VideoFileClip(video_path)
+    #     audio = mp.AudioFileClip(audio_path)
+    #     if audio.duration > video.duration:
+    #         audio = audio.subclip(0, video.duration)
+    #     final_video = video.set_audio(audio)
+    #     final_video.write_videofile(output_video, codec="libx264", audio_codec="aac")
 
-    add_audio_to_video(video_path, "summary_audio.mp3")
+    # add_audio_to_video(video_path, "summary_audio.mp3")
 
-    st.video("final_video.mp4")
+    # st.video("final_video.mp4")