buzz
buzz copied to clipboard
Access to actual large model
If "High" uses the "medium" model, is there a way that I can get higher quality? I would like to use the large model. But how? Does it require modifying the code and rebuilding it? Or is there a trick?
Hi, yes, I had disabled this because the large models seemed to be crashing the application on some machines. There isn't really a workaround, so it'll need a new build/release.
I am also looking for a way to use the large model. I believe that the large v2 model was recently released. Due to nature of speaker accents/language, a less accurate model doesn't seem to work well in my use case.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.