This project is a speech analysis and grading tool that uses OpenAI's GPT-4 and Whisper ASR models to evaluate, transcribe, and suggest improvements for both informative and persuasive speeches.
- Record or upload audio files for analysis
- Automatic transcription using Whisper ASR
- Evaluation of speech based on informativeness or persuasiveness
- Suggested improvements for the speech content
- Intuitive Gradio user interface
- Clone the repository:
git clone https://github.com/yourusername/speech-analyzer.git- Install the requirements:
pip install -r requirements.txt- Run the app:
python gradio_app.py