How to modify the whisper build script to enable NVidia CUDA support? #157
-
|
Has anyone tried to modify the build scripts to ensure that when whisper.cpp is built, it's built with CUDA support? https://github.com/ggml-org/whisper.cpp?tab=readme-ov-file#nvidia-gpu-support shows the commands needed to build with CUDA support, but I'm wondering in what specific file I should be replacing the current cmake build commands with those, in order to not break anything. I'm deploying the backend natively in Windows (no docker). So although I see mentions of enabling GPU support in docker deployments in the documentation, I don't see how to enable support for a native windows build. |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
Nevermind, I can't believe I missed it. It's explained in the documentation at https://github.com/Zackriya-Solutions/meeting-minutes/?tab=readme-ov-file#gpu-support-solution and talked about here #126 |
Beta Was this translation helpful? Give feedback.
Nevermind, I can't believe I missed it. It's explained in the documentation at https://github.com/Zackriya-Solutions/meeting-minutes/?tab=readme-ov-file#gpu-support-solution and talked about here #126