Create app.py

app.py

@@ -0,0 +1,128 @@
+import streamlit as st
+import whisper
+from moviepy.editor import VideoFileClip
+import torch
+import os
+import yt_dlp  # Updated import
+from transformers import pipeline
+
+# Load the Whisper model once with GPU support
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = whisper.load_model("base", device=device)  # Choose appropriate model size
+
+# Load the summarization pipeline
+summarizer = pipeline("summarization")
+
+# Define chunk length in seconds
+chunk_len_s = 10
+
+def download_video(youtube_url, audio_file_path):
+    """
+    Downloads a YouTube video and extracts audio, saving it as an MP3 file.
+    """
+    try:
+        ydl_opts = {
+            'format': 'bestaudio/best',
+            'outtmpl': audio_file_path.replace('.mp3', '') + '.%(ext)s',  # Ensure correct extension handling
+            'postprocessors': [{
+                'key': 'FFmpegExtractAudio',
+                'preferredcodec': 'mp3',
+                'preferredquality': '192',
+            }],
+        }
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([youtube_url])
+
+        final_audio_file_path = audio_file_path if audio_file_path.endswith('.mp3') else audio_file_path + '.mp3'
+        print(f"Audio downloaded and saved as {final_audio_file_path}")
+        return final_audio_file_path
+
+    except Exception as e:
+        print(f"Error downloading video: {e}")
+        return None
+
+def transcribe_audio_in_chunks(audio_file_path, chunk_len_s):
+    """
+    Transcribes a provided audio file in chunks using the loaded Whisper model.
+    """
+    try:
+        if not os.path.exists(audio_file_path):
+            print(f"Error: MP3 file {audio_file_path} not found")
+            return None
+
+        # Load and preprocess the audio file
+        audio = whisper.load_audio(audio_file_path)
+        audio_length = len(audio) / whisper.audio.SAMPLE_RATE
+
+        # Transcribe the audio in chunks
+        transcription = ""
+        for start in range(0, int(audio_length), chunk_len_s):
+            end = min(start + chunk_len_s, int(audio_length))
+            chunk = audio[int(start * whisper.audio.SAMPLE_RATE):int(end * whisper.audio.SAMPLE_RATE)]
+            chunk = whisper.pad_or_trim(chunk)
+            result = model.transcribe(chunk)
+            transcription += result['text'] + " "
+
+        return transcription.strip()
+    except Exception as e:
+        print(f"Error transcribing audio: {e}")
+        return None
+
+def summarize_text(text):
+    """
+    Summarizes the provided text by splitting it into smaller chunks if necessary.
+    """
+    try:
+        # Split the text into chunks of 1024 tokens
+        max_chunk_size = 1024
+        text_chunks = [text[i:i + max_chunk_size] for i in range(0, len(text), max_chunk_size)]
+        
+        # Summarize each chunk and combine the summaries
+        summaries = []
+        for chunk in text_chunks:
+            summary = summarizer(chunk, max_length=150, min_length=40, do_sample=False)[0]['summary_text']
+            summaries.append(summary)
+        
+        # Combine all summaries into one
+        combined_summary = " ".join(summaries)
+        return combined_summary
+    except Exception as e:
+        print(f"Error summarizing text: {e}")
+        return None
+
+def main(youtube_url):
+    """
+    Main workflow: Downloads audio from YouTube video, transcribes it in chunks, and summarizes the transcription.
+    """
+    audio_file_path = "audio.mp3"
+
+    # Download video and extract audio
+    downloaded_audio_path = download_video(youtube_url, audio_file_path)
+    if downloaded_audio_path:
+        # Transcribe the MP3 file in chunks
+        transcription = transcribe_audio_in_chunks(downloaded_audio_path, chunk_len_s)
+        if transcription:
+            print("Transcription:", transcription)
+            # Summarize the transcription
+            summary = summarize_text(transcription)
+            if summary:
+                return transcription, summary
+    return None, None
+
+# Streamlit interface
+st.title("YouTube Video Transcription and Summarization")
+
+youtube_url = st.text_input("Enter YouTube Video URL", "https://www.youtube.com/watch?v=your_video_id")
+if st.button("Submit"):
+    transcription, summary = main(youtube_url)
+    if transcription:
+        st.subheader("Transcription")
+        st.text_area("Transcription", transcription, height=300)
+    else:
+        st.error("Transcription failed.")
+
+    if summary:
+        st.subheader("Summary")
+        st.text_area("Summary", summary, height=150)
+    else:
+        st.error("Summary failed.")