Dmitry
Dmitry
@HinTak yes, after a look at the issue it seems that the PR I made is more a quick patch rather than actual long-term solution. I'll close it. I've been...
The fork I maintain https://github.com/AIWintermuteAI/whispercpp
Take a look at my fork, it has CI set up https://github.com/AIWintermuteAI/whispercpp
See here https://github.com/AIWintermuteAI/whispercpp/issues/88#issuecomment-2237043595
No, it is definitely not an issue with the download mechanism. The model downloaded manually fails the same way.
Fixed here https://github.com/AIWintermuteAI/whispercpp/commit/512426f3705e1ef37b499931d237734d6ebdd02e Need to build and install locally of course. @aarnphm are you still interested in maintaining the package? I see there is a cron job updating submodules, but...
@JakubVanek it's because it wasn't compiled by default. Now it is https://github.com/raspberrypi/linux/issues/4454 However the codec is likely broken and using it will result in problems with recording sound https://github.com/raspberrypi/linux/issues/4384
As an afterthought, it's likely this can be fixed by calculating correct size of scratch buffer beforehand.
Hi, @vikramdattu ! Thank you for the fast reply and help in resolution of the problem. I tested the patch and can confirm it resolves the problem. As soon you...
Hi there! Thank you for the contribution! There are some Docker files that were not present originally in the repository. Could you please clean them up and then I can...