Your AI partner for subtitle generation and text summarization . This project provides a unique solution for video content consumers, offering transcription, summarization, and audio conversion of videos. Leveraging state-of-the-art technology and a user-centric design, the application promises accurate, relevant, and timely summaries to enhance content comprehension.
- Video Transcription using OpenAI's Whisper: Transcribe any video into text.
- Fine-tuned BART Model for Video Summarization: Transform long video transcriptions into concise summaries.
- Audio Conversion: Convert the summarized text back into audio format for on-the-go consumption.
- Streamline video content consumption by eliminating the need to watch lengthy videos in their entirety.
- Deliver accurate, timely, and relevant summaries to users.
- Enhance user convenience in grasping the essence of video content.
The efficacy of the project is gauged using renowned performance metrics. These will measure:
- Accuracy: How close the summarized content is to the original content's intent.
- Relevance: How relevant the summary is to the user's requirements.
- Timeliness: How quickly the summary is provided after the video is uploaded or played.
- Python 3.x
- Flask/FastAPI
- OpenAI's Whisper API key
- Fine-tuned BART model
-
Clone the repository:
git clone [repository_link] -
create a new enviroment for the porject
conda create -p your_env_name python==3.10 -y -
Activate your new env
conda activate env/
bash : source activate env/
-
Install the required packages:
pip install -r requirements.txt -
Set up the environment variables (Whisper API key, etc.)
-
Run the application:
python main.py
- OpenAI for the Whisper Transcription Service.
- The BART model and the community for fine-tuning techniques.
Feel Free to Get in touch with be : [email protected]
Made by ❤️ @the_ghost aka Shashank