Potassium Project APP - Whisper Large-v2 with speaker diarization

Takes any base64 string as input and returns a JSON with speaker diarization and timestamps.

This is a Potassium App to be run on Banana.dev for using Whisper Large v2 on Banana's serverless GPU platform. Ready for 1-Click deploy. Based on the huggingface gradio found here and this banana.dev template and this banan.dev template.

Quickstart

Follow the quickstart guide in Banana's documentation to use this repo.

(choose "GitHub Repository" deployment method)

License

MIT License

Credits

lucato

Author

thomas_mol