AbSadiki

> ok got it! Just in case anyone comes across this later: Link 1 :[pyannote/pyannote-audio](https://github.com/pyannote/pyannote-audio?tab=readme-ov-file) Link 2: [huggingface.co/pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) Link 3: [huggingface.co/pyannote/speaker-diarization](https://huggingface.co/pyannote/speaker-diarization) > > I guess the issue now is that...

You are welcome @nexuslux. Feel free to le me know if you find any problems.

@pagkly, I already fixed this issue in #115. Could you try with `--no-cache-dir` ? Maybe pip is trying to install a cached version.

Try smaller models and if they work then this is probably a `WhsiperX` issue, go to their repo and see if they support `large-v3`. For `Whisper-timestamped`, you should see the...

@bastienperez, It seems this project is just a CLI wrapping the HF transformers implementation. I will try to add the HF pipeline directly into the project when I get some...

thanks @mkatic007 for reporting the issue. It should be fixed now.

I think docker does not detect you have a NVIDIA GPU. Does the nbody docker image run without any problem ?

Have you tried to run the docker with the argument `--gpus=all` ? You can take a look at [this example]( https://docs.docker.com/desktop/gpu/)

Unfortunately the `whisper` model has no built-in method to do this currently. What you could do though is to extract the video with each audio track separately into multiple files...

Hi @pestikoko11, I don't see any errors in the terminal! If the file is exported successfully then the subtitles are merged with the video.