Project for HackUIowa 2023
HoloGlass swfitly transcribes conversations in real-time, displaying them directly into your field of vision. Utilizing some of the best modern language models, we partition and summarize all your previous conversations.
In this repo, we explore using AWS amazon-transcribe, Google Cloud speaker diarization, Pyannote speaker diarization, and whisperx transcription.
- Cohere for dialogue summarization.
- Google Cloud Speech-to-Text for live transcription.
- Streamlit for transcript summaries and speaker annotations display.
- Python audio recording and processing with sounddevice, soundfile, and pyaudio.