There is a Freebsd package for whisper-cpp to transcribe audio but it doesnt have vulkan enabled so it uses the cpu and you would have to build it using ports or poudriere to ennable vulkan
So a quicker solution is to download the whisper-cpp git repository and build it with cmake with libs off to compile all the libraries into a self contained binary
I also take a look at the different models to use with whisper-cpp and a shell script i created called transcribe-audio which simplifies using whisper-cpp by defining a default model and options so you dont have to type as much
Building whisper-cpp with vulkan on Freebsd
cerberus/whisper-cpp/whisper-cpp-vulkan-freebsd.org at master · NapoleonWils0n/cerberus
cerberus code library. Contribute to NapoleonWils0n/cerberus development by creating an account on GitHub.
github.com
subed is an Emacs major mode for editing subtitles while playing the corresponding media file with mpv.
GitHub - sachac/subed: subed is a subtitle editor for Emacs
subed is a subtitle editor for Emacs. Contribute to sachac/subed development by creating an account on GitHub.
github.com