In this project, I have:
- Used Whisper AI to transcribe videos/audios
- Use this link to set up whisper: Setting up Whisper
- Used T5 model from hugging face for summarization of transcription
- Used this model from hugging face: Hugging Face Falconsai
- Used streamlit for frontend cover
- If you want to understand it step-by-step, follow this article: Medium Link