Skip to content

Latest commit

 

History

History
60 lines (38 loc) · 1.75 KB

README.md

File metadata and controls

60 lines (38 loc) · 1.75 KB

Overview

This project is a YouTube Video Summarization App that leverages LangChain, Llama3.2, YouTube Transcript API, and Streamlit to provide concise summaries of YouTube video transcripts. The app extracts the transcript from a given YouTube video URL and generates a summary using a local language model.

Features

  • Extracts transcripts from YouTube videos
  • Summarizes transcripts using a local LLM (Llama3.2, Mistral, or CodeLlama)
  • Adjustable summary length
  • User-friendly interface with Streamlit
  • Options to download the transcript and summary

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/YouTube-Video-Summarization-App.git
cd YouTube-Video-Summarization-App

  2. Install the required dependencies:

    pip install -r requirements.txt

Usage

  1. Run the Streamlit app:

    streamlit run app.py

  2. Open your web browser and go to http://localhost:8501.

  3. Enter the YouTube video URL and adjust the settings as needed.

  4. Click the button to generate the summary and view the results.

Configuration

  • Model Selection: Choose between Llama3.2, Mistral, or CodeLlama for summarization.
  • Summary Length: Adjust the length of the generated summary using the slider in the sidebar.

Contributing

Contributions are welcome! Please fork the repository and submit a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgements