Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from pytube import YouTube | |
| from moviepy.editor import * | |
| import torch | |
| from transformers import Wav2Vec2ForCTC, Wav2Vec2CTCTokenizer, pipeline, logging | |
| import librosa | |
| # Suppress warnings from transformers | |
| logging.set_verbosity_error() | |
| # Streamlit interface setup | |
| st.title("YouTube Video Summarizer") | |
| youtube_link = st.text_input("Enter YouTube Video Link:") | |
| if st.button('Summarize'): | |
| if not youtube_link: | |
| st.warning("Please enter a valid YouTube link.") | |
| else: | |
| with st.spinner("Processing..."): | |
| try: | |
| # Download YouTube Video | |
| yt = YouTube(youtube_link) | |
| video = yt.streams.filter(only_audio=True).first() | |
| download_path = video.download() | |
| # Show progress | |
| st.progress(25) | |
| # Extract Audio | |
| video_clip = AudioFileClip(download_path) | |
| audio_path = download_path.replace('.mp4', '.wav') | |
| video_clip.write_audiofile(audio_path) | |
| # Show progress | |
| st.progress(50) | |
| # Speech to Text | |
| tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("facebook/bart-large-cnn") | |
| model = Wav2Vec2ForCTC.from_pretrained("facebook/bart-large-cnn") | |
| # Load and process the audio | |
| speech, _ = librosa.load(audio_path, sr=16000) | |
| input_values = tokenizer(speech, return_tensors="pt").input_values | |
| logits = model(input_values).logits | |
| predicted_ids = torch.argmax(logits, dim=-1) | |
| # Decode the speech | |
| transcription = tokenizer.batch_decode(predicted_ids, skip_special_tokens=True)[0] | |
| # Ensure transcription is a string, not empty, and not too short | |
| if isinstance(transcription, str) and transcription.strip() and len(transcription) > 50: | |
| # Show progress | |
| st.progress(75) | |
| # Initialize the summarizer | |
| summarizer = pipeline("summarization") | |
| # Summarization | |
| summary = summarizer(transcription, max_length=130, min_length=30, do_sample=False) | |
| st.success("Done!") | |
| st.write("### Summary:") | |
| st.write(summary[0]['summary_text']) | |
| # Final progress | |
| st.progress(100) | |
| else: | |
| st.error("Transcription result is empty, too short, or not a string.") | |
| except Exception as e: | |
| st.error(f"An error occurred: {e}") | |