Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #31.
Now you can switch between CPU inference and CUDA inference. To run CUDA inference, you need supported card and installed CUDA Toolkit (tested with 12.2.0). To activate CUDA inference go to Project Settings => Whisper => Enable CUDA.
whisper.cpp will not fallback to CPU in your Editor/Build. If you want to distribute your CUDA build make sure to force user install CUDA Toolkit or distribute CUDA dlls by yourself.
This PR changes
build_cpp.bat
file and add new Github Action to build whisper.cpp with CUDA.Also:
whisper_init_from_file_with_params
andwhisper_init_from_buffer_with_params
. Previous methods were marked deprecated.whisper_print_system_info
to get human readable information about compiled whisper libraries. Helps to check if libs were compiled with AVX, CUDA flag, etc. Unfortunately, it doesn't check actual hardware capacity.