Raivis Dejus

@shuke12306 Something is wrong with your `ffmpeg`. Option 1 - try installing it with `choco install ffmpeg` more info here https://github.com/chidiwilliams/buzz/blob/main/CONTRIBUTING.md Option 2 - Run the ffmpeg on command line...

@vincechang1015 An issue with faster whisper was fixed in latest development version https://github.com/chidiwilliams/buzz/actions/runs/10211346492. You may need to delete the downloaded models and re-download them again

@vincechang1015 Faster whisper will not work on Windows with CUDA. The required cuBLAS (or HPC SDK) for Windows is currently not available. Regular whisper and Huggingface models should work with...

@Zsural Faster whisper supports only CUDA 12. I think your best option is to update CUDA. To use CUDA 11 you would need to run the source version and downgrade...

Will close the issue, feel free to open new ones if you encounter this and none of the suggestions work on the latest development version from https://github.com/chidiwilliams/buzz/actions/workflows/ci.yml?query=branch%3Amain To download artifacts...

Maybe @lmstudio-ai can sort this out on their end...