fortypercnt

Results 9 comments of fortypercnt

I narrowed this down to the move from gradio 3.4.1 to 3.5. Reverting 4ed99d599640bb86bc793aa3cbed31c6d0bd6957 and e8729dd0511f8410db967d9ef192645cfef1be8a fixes the issue.

> > I narrowed this down to the move from gradio 3.4.1 to 3.5. Reverting [4ed99d5](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/4ed99d599640bb86bc793aa3cbed31c6d0bd6957) and [e8729dd](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/e8729dd0511f8410db967d9ef192645cfef1be8a) fixes the issue. > > is there a way to do just...

> > Gradio 3.5 is needed for iPads. But I've come to the same conclusion that the problems with the inpaint display is tied to the Gradio update by rolling...

Agree, closing this since #4151 is a better solution.

Sorry for the delayed response. For the incorrect language identification issue, you should be able to fix that by setting the --language flag to the language spoken in the stream....

Thanks for the link. I had the idea to make an on screen display instead of just the command line output pretty much from the start, but it is not...

Yea Whisper has a tendency to hallucinate on non-speech segments. That is why I added extra voice activity detection by Silero VAD. Maybe you can improve the issue by setting...

> This will stream your regular computer desktop audio, whatever you have playing, from any source. I'm sure someone who knows OSB can setup OBS in a more selective way...

Thanks for the kind words! This project uses streamlink to get livestream CDN URLs which are then passed to ffmpeg/whisper. Streamlink does not currently support Kick and judging by [this...