app-accessibility/whisper-cpp
Port of OpenAI's Whisper model in C/C++
-
whisper-cpp-9999blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: stuff -
whisper-cpp-9999blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: guru -
whisper-cpp-1.9.0~amd64 ~arm64blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: stuff -
whisper-cpp-1.8.7~amd64blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: stuff -
whisper-cpp-1.8.6~amd64 ~arm64blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: stuff -
whisper-cpp-1.8.5~amd64blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: stuff -
whisper-cpp-1.8.4~amd64blas cuda ffmpeg hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: guru -
whisper-cpp-1.8.3-r2~amd64blas cuda hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: guru -
whisper-cpp-1.7.6~amd64blas cuda hip opencl sdl2 vulkan
View
Download
Browse License: MIT Overlay: guru
ChangeLog
commit cc94c50590432d63de729cbc5ddbf4b21dda01ce
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Jun 18 10:36:01 2026 +0200
app-accessibility/whisper-cpp: Keyword 1.9.0 for ~arm64
commit b1025768dea5c8a37932a5ea6462977719822980
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Jun 16 22:57:10 2026 +0200
app-accessibility/whisper-cpp: Keyword 1.8.6 for ~arm64
aarch64-portable; no architecture-specific code.
commit 4793be8c7ee3d0c95732106f1a74ce9360c32a76
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Jun 18 07:56:48 2026 +0200
app-accessibility/whisper-cpp: add 1.9.0
commit 5ecaee2b96c4feeee644eb8659566372951e6031
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Jun 16 14:10:51 2026 +0200
app-accessibility/whisper-cpp: add 1.8.7
commit fdbb08e7aa13b3c3de9882e8c92337a048f46727
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Mon Jun 15 23:53:50 2026 +0200
app-accessibility/whisper-cpp: generalize CUDA host-compiler comment
Drop host-specific wording from the CUDAHOSTCXX rationale comment; the
dated verification note and the gcc>15 pin reason are kept.
commit a4995a1b5ead400a8625fe1030c8a6432b7b755a
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jun 6 21:00:15 2026 +0200
app-accessibility/whisper-cpp: drop 1.8.4
commit b8c84925d74354c129056f2e7171f6e1159daef4
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Mon Jun 1 23:59:30 2026 +0200
app-accessibility/whisper-cpp: add 1.8.6
Adopts the new upstream option name WHISPER_COMMON_FFMPEG; the legacy
WHISPER_FFMPEG knob remains a deprecated alias for now, but tracking
the canonical name keeps the warning out of the build log and matches
the example/common refactor (examples/CMakeLists.txt no longer
references WHISPER_FFMPEG).
commit 8d2e44f46002a92f6456b7a13147ea0970730bf6
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri May 29 13:43:59 2026 +0200
app-accessibility/whisper-cpp: add 1.8.5
commit 22414d8cbda8cd689705199244ab2eb5e31353f3
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu May 14 17:01:19 2026 +0200
app-accessibility/whisper-cpp: new package, add 1.8.4 and 9999
Forked from guru; fixes vs. upstream:
- -DGGML_CUBLAS (silently ignored) → -DGGML_CUDA (verified 2026-05-14)
- BDEPEND shaderc gated on vulkan? (glslc only needed in ggml-vulkan backend)
- -DGGML_NATIVE=OFF to prevent -march=native injection; with
GGML_NATIVE_DEFAULT=ON and GGML_NATIVE=OFF, ggml's hand-optimised
AVX2/FMA/F16C kernels compile via INS_ENB=ON
- -DGGML_CCACHE=OFF in the sandbox
- -DWHISPER_BUILD_TESTS=OFF (tests require model files not in tarball)
- CMAKE_CUDA_HOST_COMPILER pinned to g++-15 when cuda USE is set
(CUDA 13.x nvcc rejects gcc>15; verified 2026-05-14)
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Jun 18 10:36:01 2026 +0200
app-accessibility/whisper-cpp: Keyword 1.9.0 for ~arm64
commit b1025768dea5c8a37932a5ea6462977719822980
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Jun 16 22:57:10 2026 +0200
app-accessibility/whisper-cpp: Keyword 1.8.6 for ~arm64
aarch64-portable; no architecture-specific code.
commit 4793be8c7ee3d0c95732106f1a74ce9360c32a76
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu Jun 18 07:56:48 2026 +0200
app-accessibility/whisper-cpp: add 1.9.0
commit 5ecaee2b96c4feeee644eb8659566372951e6031
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Tue Jun 16 14:10:51 2026 +0200
app-accessibility/whisper-cpp: add 1.8.7
commit fdbb08e7aa13b3c3de9882e8c92337a048f46727
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Mon Jun 15 23:53:50 2026 +0200
app-accessibility/whisper-cpp: generalize CUDA host-compiler comment
Drop host-specific wording from the CUDAHOSTCXX rationale comment; the
dated verification note and the gcc>15 pin reason are kept.
commit a4995a1b5ead400a8625fe1030c8a6432b7b755a
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jun 6 21:00:15 2026 +0200
app-accessibility/whisper-cpp: drop 1.8.4
commit b8c84925d74354c129056f2e7171f6e1159daef4
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Mon Jun 1 23:59:30 2026 +0200
app-accessibility/whisper-cpp: add 1.8.6
Adopts the new upstream option name WHISPER_COMMON_FFMPEG; the legacy
WHISPER_FFMPEG knob remains a deprecated alias for now, but tracking
the canonical name keeps the warning out of the build log and matches
the example/common refactor (examples/CMakeLists.txt no longer
references WHISPER_FFMPEG).
commit 8d2e44f46002a92f6456b7a13147ea0970730bf6
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Fri May 29 13:43:59 2026 +0200
app-accessibility/whisper-cpp: add 1.8.5
commit 22414d8cbda8cd689705199244ab2eb5e31353f3
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Thu May 14 17:01:19 2026 +0200
app-accessibility/whisper-cpp: new package, add 1.8.4 and 9999
Forked from guru; fixes vs. upstream:
- -DGGML_CUBLAS (silently ignored) → -DGGML_CUDA (verified 2026-05-14)
- BDEPEND shaderc gated on vulkan? (glslc only needed in ggml-vulkan backend)
- -DGGML_NATIVE=OFF to prevent -march=native injection; with
GGML_NATIVE_DEFAULT=ON and GGML_NATIVE=OFF, ggml's hand-optimised
AVX2/FMA/F16C kernels compile via INS_ENB=ON
- -DGGML_CCACHE=OFF in the sandbox
- -DWHISPER_BUILD_TESTS=OFF (tests require model files not in tarball)
- CMAKE_CUDA_HOST_COMPILER pinned to g++-15 when cuda USE is set
(CUDA 13.x nvcc rejects gcc>15; verified 2026-05-14)

