In this project, we'll build a system that can automatically recognize speech and summarize it. This can be used for automatically transcribing and summarizing lecture recordings, podcasts, or videos. By the end of this project, you'll have a speech to text project that you can continue to build on.
Project Steps
- Create a speech recognition system using vosk.
- Add punctuation to the text transcript using recasepunc.
- Summarize the text using a huggingface summarization pipeline.
Future Scope We'll also include a way to hook up a microphone to automatically record and transcribe audio for live notetaking. This could be used to record and transcribe meetings in real-time.