Initial Commit

app.py

@@ -0,0 +1,141 @@
+import streamlit as st
+import os
+import time
+import logging
+from moviepy.video.io.VideoFileClip import VideoFileClip
+import whisper
+from transformers import pipeline
+import cv2
+import numpy as np
+
+# Set up logging configuration
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger()
+
+# Set up directories
+UPLOAD_FOLDER = './uploads'
+PROCESSED_FOLDER = './processed'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+os.makedirs(PROCESSED_FOLDER, exist_ok=True)
+
+# Initialize the summarizer model from Hugging Face
+summarizer = pipeline("summarization", model="meta-llama/Llama-3.2-1B")
+
+# Function to extract audio from video using MoviePy
+def extract_audio_from_video(video_file_path, audio_file_path):
+    try:
+        logger.info(f"Extracting audio from video: {video_file_path}")
+        video_clip = VideoFileClip(video_file_path)
+        audio_clip = video_clip.audio
+        audio_clip.write_audiofile(audio_file_path)
+        logger.info(f"Audio extraction completed and saved to: {audio_file_path}")
+    except Exception as e:
+        logger.error(f"Error extracting audio from video: {e}")
+
+# Function to transcribe audio using Whisper
+def transcribe_audio(audio_file_path):
+    try:
+        logger.info(f"Transcribing audio: {audio_file_path}")
+        model = whisper.load_model("base")  # Load the Whisper model
+        result = model.transcribe(audio_file_path)
+        logger.info("Audio transcription completed.")
+        return result['text']
+    except Exception as e:
+        logger.error(f"Error transcribing audio: {e}")
+        return ""
+
+# Function to summarize the transcription text using Hugging Face Transformers
+def split_text_into_chunks(text, chunk_size=1000):
+    chunks = []
+    for i in range(0, len(text), chunk_size):
+        chunks.append(text[i:i+chunk_size])
+    return chunks
+
+def summarize_text(text):
+    try:
+        chunks = split_text_into_chunks(text)
+        summaries = []
+        for chunk in chunks:
+            summary = summarizer(chunk, max_new_tokens=500, min_length=50, do_sample=False)
+            summaries.append(summary[0]['summary_text'])
+        return " ".join(summaries)
+    except Exception as e:
+        st.error(f"Error summarizing text: {e}")
+        return "Error occurred during summarization."
+
+
+# Function to detect scene changes in the video using OpenCV (optional)
+def detect_scene_changes(video_file_path):
+    try:
+        logger.info(f"Detecting scene changes in video: {video_file_path}")
+        cap = cv2.VideoCapture(video_file_path)
+        ret, prev_frame = cap.read()
+        prev_frame_gray = cv2.cvtColor(prev_frame, cv2.COLOR_BGR2GRAY)
+        
+        scene_changes = []
+        frame_count = 0
+        
+        while ret:
+            ret, frame = cap.read()
+            if not ret:
+                break
+            frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+            diff = cv2.absdiff(frame_gray, prev_frame_gray)
+            non_zero_count = np.count_nonzero(diff)
+            
+            if non_zero_count > 1000000:  # Threshold for detecting scene change
+                scene_changes.append(frame_count)
+            
+            prev_frame_gray = frame_gray
+            frame_count += 1
+
+        cap.release()
+        logger.info(f"Scene changes detected: {scene_changes}")
+        return scene_changes
+    except Exception as e:
+        logger.error(f"Error detecting scene changes: {e}")
+        return []
+
+# Streamlit App
+st.title("Automated Video Summarization")
+
+# File upload widget
+uploaded_file = st.file_uploader("Choose a video file", type=["mp4", "avi", "mov"])
+
+if uploaded_file is not None:
+    try:
+        # Save the uploaded file to the upload folder with a timestamp
+        timestamp = int(time.time())
+        filename = f"{timestamp}_{uploaded_file.name}"
+        video_path = os.path.join(UPLOAD_FOLDER, filename)
+
+        # Save the uploaded file
+        with open(video_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        
+        logger.info(f"File uploaded successfully: {filename}")
+        st.write(f"File uploaded successfully: {filename}")
+
+        # Extract audio from the video
+        audio_file_path = os.path.join(PROCESSED_FOLDER, f"{filename}.wav")
+        extract_audio_from_video(video_path, audio_file_path)
+        st.write("Audio extracted successfully.")
+
+        # Transcribe the audio
+        transcription = transcribe_audio(audio_file_path)
+        st.write("Transcription completed.")
+
+        # Add a spinner while the summarization is happening
+        with st.spinner('Generating summary, please wait...'):
+            summary = summarize_text(transcription)
+        st.subheader("Summary")
+        st.write(summary)
+
+        # Optional: Detect scene changes in the video
+        scene_changes = detect_scene_changes(video_path)
+        st.subheader("Scene Changes Detected at Frames")
+        st.write(scene_changes)
+
+    except Exception as e:
+        logger.error(f"An error occurred: {e}")
+        st.error(f"An error occurred: {e}")

requiements.txt

@@ -0,0 +1,7 @@
+streamlit==1.25.0
+moviepy==1.0.3
+transformers==4.33.0
+torch==2.0.1
+whisper==1.0
+opencv-python-headless==4.8.0
+numpy==1.26.0