The audio/whisper.cpp port
whisper.cpp-1.7.6 – automatic speech recognition (openai whisper model) (cvsweb github mirror)
Description
High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model. Features include: - Plain C/C++ implementation depending only on GGML - AVX intrinsics support for amd64 - VSX intrinsics support for POWER architectures - Mixed F16 / F32 precision - Integer quantization support - Zero memory allocations at runtime - Vulkan support - Support for CPU-only inference - C-style API - Voice Activity Detection (VAD)WWW: https://github.com/ggml-org/whisper.cpp
Readme
+-------------------------------------------------------------------------------
| Running ${PKGSTEM} on OpenBSD
+-------------------------------------------------------------------------------
whisper.cpp requires use of an AI model for operation. This package
includes a base model for English transcription; others are available
by using the bundled download script:
For example, to fetch the multilingual base model:
$ whisper.cpp-download-ggml-model base
Files fetched in this way can be used by passing the -m flag:
$ whisper-cli -m ggml-base.bin -f {sample}.wav
Maintainer
The OpenBSD ports mailing-list
Only for arches
aarch64 alpha amd64 arm hppa i386 mips64 mips64el powerpc powerpc64 riscv64 sparc64
Categories
Library dependencies
Build dependencies
Files
- /usr/local/bin/vad-speech-segments
- /usr/local/bin/whisper-bench
- /usr/local/bin/whisper-cli
- /usr/local/bin/whisper-server
- /usr/local/bin/whisper.cpp-download-ggml-model
- /usr/local/include/whisper.h
- /usr/local/lib/cmake/whisper/
- /usr/local/lib/cmake/whisper/whisper-config.cmake
- /usr/local/lib/cmake/whisper/whisper-version.cmake
- /usr/local/lib/libwhisper.so.0.0
- /usr/local/lib/pkgconfig/whisper.pc
- /usr/local/share/doc/pkg-readmes/whisper.cpp
- /usr/local/share/whisper.cpp/
- /usr/local/share/whisper.cpp/ggml-base.en.bin