Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

10.7 MB

100 contributors

History: 695 commits

ggerganov's picture

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247)

8bb66c1 unverified over 2 years ago

.github
OSSRH_USERNAME -> JIRA_USER over 2 years ago
bindings
ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
cmake
cmake : update to 3.19 (#351) almost 3 years ago
coreml
coreml : wrap inference call in @autoreleasepool to fix memory leak (#1218) over 2 years ago
examples
ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
extra
extra : update 'quantize-all.sh' to quantize all downloaded models (#1054) over 2 years ago
models
whisper : add OpenVINO support (#1037) over 2 years ago
openvino
whisper : add OpenVINO support (#1037) over 2 years ago
samples
Create README.md about 3 years ago
tests
tests : add "threads" to run-tests.sh over 2 years ago
.gitattributes

804 Bytes

Initial release about 3 years ago
.gitignore

661 Bytes

examples : vim plugin and LSP server (#1144) over 2 years ago
.gitmodules

96 Bytes

cmake : add submodule whisper.spm about 3 years ago
CMakeLists.txt

14.7 kB

whisper : initial hipBLAS support (#1209) over 2 years ago
LICENSE

1.07 kB

license : update year (#739) over 2 years ago
Makefile

12.6 kB

make : improve cpuinfo handling on x86 hosts (#1238) over 2 years ago
README.md

34.8 kB

readme : update CMake build commands (#1231) over 2 years ago
ggml-alloc.c

22.1 kB

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
ggml-alloc.h

905 Bytes

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
ggml-cuda.cu

257 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
ggml-cuda.h

1.72 kB

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
ggml-metal.h

3.43 kB

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
ggml-metal.m

62.1 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
ggml-metal.metal

78.5 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
ggml-opencl.cpp

68.9 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
ggml-opencl.h

845 Bytes

ggml : sync latest ggml lib over 2 years ago
ggml.c

684 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
ggml.h

72.3 kB

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247) over 2 years ago
whisper.cpp

191 kB

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220) over 2 years ago
whisper.h

26 kB

whisper : significantly improve the inference quality (#1148) over 2 years ago