Raivis Dejus
Raivis Dejus
Most likely something with the model. Things to try: - Get the latest version `1.1.0` - Try shorter audio to see if model works fine in principle - Try different...
Translation feature and abilty to specify custom baseurl for OpenAI API has been added to the latest main branch. See instructions on how to use translations or get the latest...
Closing as stale, please re-open with more information if still relevant
Please see notes on local build here https://github.com/chidiwilliams/buzz/blob/main/CONTRIBUTING.md
Latest version 1.0.0 or later (or snap versions after 2024-07-06) will warn user about missing SNAP permissions as well as have `large-v2` or `large-v3` models selectaable
If it is Windows, please see if Buzz has permission to use the microphone in Settings -> Privacy -> Microphone See method 1 in this video https://www.youtube.com/watch?v=eRcCYgOuSYQ For method 2...
Windows version: ignore GPU during processing (still not fix as that issue is nr. 3 from what I see)
Linux version has full support for use of GPU. As models can be big and if they do not fit the GPU VRAM app will crash, for now Buzz for...
Windows version: ignore GPU during processing (still not fix as that issue is nr. 3 from what I see)
Latest version 1.0.0 should support CUDA GPUs with no VRAM checks. https://github.com/chidiwilliams/buzz/releases Please re-open the issue if Windows GPU still has some issues
@DeafNet you would like to load (import) some text? Regular text with no timestamps? Or subtitle files with timestamps. If you want to align existing good text with audio you...
For Apple silicon please try the latest version `1.1.0` For Intel get the version from latest development build (you need to log into the github to see the artifact download...