A powerful Streamlit application that allows users to analyze and interact with YouTube video content through natural language questions.
- YouTube Video Processing: Input any valid YouTube URL to analyze its content
- Audio Transcription: Automatically transcribes video content using Whisper AI
- Interactive Q&A: Ask questions about the video content using advanced RAG (Retrieval-Augmented Generation)
- GPU Acceleration: Utilizes CUDA for faster processing when available
- User-Friendly Interface: Clean and intuitive Streamlit interface
- Clone the repository:
git clone https://github.com/codewithdark-git/TalkTube.git
cd TalkTube- Install the required dependencies:
pip install -r requirements.txt- Set up environment variables:
Create a
.envfile in the root directory with necessary API keys and configurations.
- streamlit
- streamlit-extras
- yt-dlp
- whisper
- torch
- python-dotenv
- (other dependencies as specified in requirements.txt)
- Run the Streamlit app:
streamlit run app.py- Enter a YouTube URL in the input field
- Wait for the video to be processed and transcribed
- Ask questions about the video content in the chat interface
- Video Processing: The app downloads the audio from YouTube videos using yt-dlp
- Transcription: Uses OpenAI's Whisper model to transcribe the audio content
- Question Answering: Implements RAG (Retrieval-Augmented Generation) to provide accurate answers based on the video content
- Built with Streamlit for the web interface
- Uses Whisper AI for accurate speech-to-text transcription
- Implements advanced RAG techniques for question answering
- Supports both CPU and GPU processing
- Handles various YouTube URL formats
- Processing time depends on video length and available computing resources
- GPU acceleration significantly improves transcription speed
- Internet connection required for YouTube video download and processing