diff options
| -rw-r--r-- | whisper.cpp/README | 8 | ||||
| -rw-r--r-- | whisper.cpp/whisper.cpp.SlackBuild | 3 |
2 files changed, 10 insertions, 1 deletions
diff --git a/whisper.cpp/README b/whisper.cpp/README index 6daff42..3894eba 100644 --- a/whisper.cpp/README +++ b/whisper.cpp/README @@ -5,10 +5,16 @@ recognition (ASR) model, plus NVIDIA Parakeet models. - AVX intrinsics support for x86 architectures - Mixed F16 / F32 precision - Integer quantization support + - Vulkan GPU backend - OpenVINO encoder support Installs whisper-cli, whisper-server, whisper-bench, whisper-quantize, -whisper-vad-speech-segments, parakeet-cli and parakeet-quantize. +whisper-vad-speech-segments, parakeet-cli and parakeet-quantize, plus +the SDL2 microphone tools whisper-stream (live transcription), +whisper-command (voice commands), whisper-talk-llama and whisper-lsp. + +The tools decode input audio through ffmpeg, so any format ffmpeg reads +is accepted, not only WAV, MP3 and FLAC. OpenVINO support is built in. The encoder must be converted to OpenVINO IR format first, see "OpenVINO Support" in the bundled README.md. diff --git a/whisper.cpp/whisper.cpp.SlackBuild b/whisper.cpp/whisper.cpp.SlackBuild index 76893eb..f4de5fe 100644 --- a/whisper.cpp/whisper.cpp.SlackBuild +++ b/whisper.cpp/whisper.cpp.SlackBuild @@ -100,6 +100,9 @@ cd build -DWHISPER_ALL_WARNINGS=OFF \ -DGGML_BUILD_EXAMPLES=OFF \ -DGGML_BUILD_TESTS=OFF \ + -DGGML_VULKAN=ON \ + -DWHISPER_SDL2=ON \ + -DWHISPER_COMMON_FFMPEG=ON \ $BLAS \ -DWHISPER_OPENVINO=ON \ -DOpenVINO_DIR=$OVDIR/cmake \ |