Gentoo Packages

sci-misc/whisper-cpp (pf4public)

Search

Install

Install this package:

emerge -a sci-misc/whisper-cpp

Package Information

Description:
whisper.cpp is a port of OpenAI's Whisper automatic speech recognition (ASR) model to plain C/C++, built on top of the vendored ggml tensor library. It provides the C APIs libwhisper and libparakeet (Parakeet TDT), the command line tools whisper-cli, whisper-bench, whisper-quantize, whisper-server, whisper-vad-speech-segments, parakeet-cli and parakeet-quantize, and optional GPU backends (CUDA, Vulkan, OpenCL) in addition to the CPU backend.
Homepage:
https://github.com/ggml-org/whisper.cpp
License:
MIT

Versions

Version EAPI Keywords Slot
9999 8 ~amd64 ~arm64 0
1.9.5 8 amd64 ~arm64 0

Metadata

Description

Maintainers

Upstream

Raw Metadata XML 
<pkgmetadata>
	<maintainer type="person">
		<email>PF4Public@users.noreply.github.com</email>
	</maintainer>
	<longdescription>
		whisper.cpp is a port of OpenAI's Whisper automatic speech recognition
		(ASR) model to plain C/C++, built on top of the vendored ggml tensor
		library. It provides the C APIs libwhisper and libparakeet (Parakeet
		TDT), the command line tools whisper-cli, whisper-bench,
		whisper-quantize, whisper-server, whisper-vad-speech-segments,
		parakeet-cli and parakeet-quantize, and optional GPU backends
		(CUDA, Vulkan, OpenCL) in addition to the CPU backend.
	</longdescription>
	<use>
		<flag name="cuda">Enable the NVIDIA CUDA backend (GGML_CUDA)</flag>
		<flag name="ffmpeg">Link the examples against FFmpeg to decode more audio formats</flag>
		<flag name="openblas">Use OpenBLAS as the BLAS backend (GGML_BLAS)</flag>
		<flag name="opencl">Enable the OpenCL backend (GGML_OPENCL)</flag>
		<flag name="openmp">Use OpenMP for threading (GGML_OPENMP)</flag>
		<flag name="rpc">Enable the RPC backend to distribute layers across machines (GGML_RPC)</flag>
		<flag name="sdl">Build the SDL2-based examples whisper-stream, whisper-command, whisper-lsp and wchess</flag>
		<flag name="system-ggml">Link against the installed sci-ml/ggml instead of the bundled copy; the CPU ISA set and the backends are then selected by ggml's own USE flags</flag>
		<flag name="vulkan">Enable the Vulkan backend (GGML_VULKAN)</flag>
	</use>
	<upstream>
		<bugs-to>https://github.com/ggml-org/whisper.cpp/issues</bugs-to>
		<remote-id type="github">ggml-org/whisper.cpp</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

USE Flags

Manage flags for this package: euse -i <flag> -p sci-misc/whisper-cpp | euse -E <flag> -p sci-misc/whisper-cpp | euse -D <flag> -p sci-misc/whisper-cpp

Flag Description 9999 1.9.5
"( ⚠️ ✓ ✓
( ⚠️ ✓ ✓
) ⚠️ ✓ ✓
)" ⚠️ ✓ ✓
amx_bf16 ⚠️ ✓ ✓
amx_int8 ⚠️ ✓ ✓
amx_tile ⚠️ ✓ ✓
avx ⚠️ ✓ ✓
avx2 ⚠️ ✓ ✓
avx512_bf16 ⚠️ ✓ ✓
avx512_vnni ⚠️ ✓ ✓
avx512f ⚠️ ✓ ✓
avx512vbmi ⚠️ ✓ ✓
avx_vnni ⚠️ ✓ ✓
bmi2 ⚠️ ✓ ✓
cuda Enable the NVIDIA CUDA backend (GGML_CUDA) ✓ ✓
f16c ⚠️ ✓ ✓
ffmpeg Link the examples against FFmpeg to decode more audio formats ✓ ✓
fma3 ⚠️ ✓ ✓
openblas Use OpenBLAS as the BLAS backend (GGML_BLAS) ✓ ✓
opencl Enable the OpenCL backend (GGML_OPENCL) ✓ ✓
openmp Use OpenMP for threading (GGML_OPENMP) ⊕ ⊕
rpc Enable the RPC backend to distribute layers across machines (GGML_RPC) ✓ ✓
sdl Build the SDL2-based examples whisper-stream, whisper-command, whisper-lsp and wchess ✓ ✓
sse4_2 ⚠️ ✓ ✓
system-ggml Link against the installed sci-ml/ggml instead of the bundled copy; the CPU ISA set and the backends are then selected by ggml's own USE flags ✓ ✓
vulkan Enable the Vulkan backend (GGML_VULKAN) ✓ ✓

Files

Manifest

Type File Size Versions
DIST whisper-cpp-1.9.5.tar.gz 9626464 bytes 1.9.5
Unmatched Entries
Type File Size