AbSadiki
AbSadiki
@yashwanth2804 I am on Ubuntu 18.10, I had the same issue, this is how I resolved it: 1/ sudo apt-get install libpng-dev 2/ npm install -g pngquant-bin 3/ sudo rm...
I don't know to be honest, but I think the "models" are just different implementations of the Whisper architecture and the model weights are still the same from openAI, so...
I didn't know about NLLB 200 .. it seems interesting. Thanks for letting me know. Yes, I think I can add it to the translation models if you need it!...
Here you go @MidnightKittenCat, [nllb200](https://huggingface.co/facebook/nllb-200-distilled-600M) has been added to the translation models. I am really surprised how good it is :) I don't think opus can come even close :D...
You are welcome :) Take your time .. just wanted to make sure it's working without a problem on your side.
It is in the webui as well. Make sure to update the package first, then from `post processing` tools, choose `translation` and select the `nllb200` from the drop down menu,...
Thanks @Camology for reporting the issue. I think there issue is caused by the latest commits in the `whisperX` repo. I updated the requirements.txt file to have the commit hash...
Thanks @ptbsare for pointing that out. I think you are right, I will roll back `faster-whisper` to v0.5.1
@nexuslux, could you please try now? I've updated it to the latest release and it works on my end.
@nexuslux, I think you didn't accept the agreement of the pyannote models on HF, take a look at the console and you should see the link for that.