Spaces:

natasa365
/

whisper.cpp

Running

App Files Files Community

14.1 MB

100 contributors

History: 886 commits

JohannesGaessler's picture

JohannesGaessler

CUDA: faster softmax via shared memory + fp16 math (llama/4742)

52c45b9 unverified almost 2 years ago

.devops
docker : fix the publishing of the CUDA Docker image (#1704) almost 2 years ago
.github
ci : build with CLBlast + ggml-opencl use GGML_API (#1576) almost 2 years ago
bindings
release : v1.5.4 almost 2 years ago
cmake
cmake : update to 3.19 (#351) almost 3 years ago
coreml
coreml : fix ANE optimized encoder (#1716) almost 2 years ago
examples
talk-llama : add optional Piper TTS support (#1749) almost 2 years ago
extra
fix : cuda order of synchronization when setting a buffer (ggml/679) almost 2 years ago
grammars
whisper : add grammar-based sampling (#1229) about 2 years ago
models
coreml : fix ANE optimized encoder (#1716) almost 2 years ago
openvino
whisper : replace `tensor->n_dims` with `ggml_n_dims(tensor)` (#1694) almost 2 years ago
samples
Create README.md about 3 years ago
spm-headers
ios : add support for Swift Package Manager (#1370) about 2 years ago
tests
whisper : make large version explicit + fix data size units (#1493) about 2 years ago
.gitattributes

804 Bytes

Initial release about 3 years ago
.gitignore

803 Bytes

server : add a REST Whisper server example with OAI-like API (#1380) about 2 years ago
.gitmodules

96 Bytes

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

19 kB

release : v1.5.4 almost 2 years ago
LICENSE

1.07 kB

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

14.7 kB

sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691) almost 2 years ago
Package.swift

1.81 kB

swift : checkout ggml commit instead of branch (#1750) almost 2 years ago
README.md

37 kB

release : v1.5.4 almost 2 years ago
ggml-alloc.c

28.6 kB

sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677) almost 2 years ago
ggml-alloc.h

3.85 kB

sync : ggml (Metal fixes, new ops, tests) (#1633) about 2 years ago
ggml-backend-impl.h

4.9 kB

ggml : add error handling to graph_compute (#1714) almost 2 years ago
ggml-backend.c

52.5 kB

ggml : add error handling to graph_compute (#1714) almost 2 years ago
ggml-backend.h

8.99 kB

ggml : add error handling to graph_compute (#1714) almost 2 years ago
ggml-cuda.cu

401 kB

CUDA: faster softmax via shared memory + fp16 math (llama/4742) almost 2 years ago
ggml-cuda.h

2.51 kB

sync : ggml (new ops, new backend, etc) (#1602) about 2 years ago
ggml-impl.h

7.51 kB

ggml : include stdlib.h before intrin.h (llama/4736) almost 2 years ago
ggml-metal.h

4.33 kB

ggml : add error handling to graph_compute (#1714) almost 2 years ago
ggml-metal.m

149 kB

metal : fix deprecation warning (ggml/690) almost 2 years ago
ggml-metal.metal

194 kB

SOTA 2-bit quants (llama/4773) almost 2 years ago
ggml-opencl.cpp

71 kB

sync : ggml (new ops, new backend, etc) (#1602) about 2 years ago
ggml-opencl.h

926 Bytes

ci : build with CLBlast + ggml-opencl use GGML_API (#1576) almost 2 years ago
ggml-quants.c

290 kB

SOTA 2-bit quants (llama/4773) almost 2 years ago
ggml-quants.h

11 kB

SOTA 2-bit quants (llama/4773) almost 2 years ago
ggml.c

655 kB

ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693) almost 2 years ago
ggml.h

82.7 kB

ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693) almost 2 years ago
whisper.cpp

231 kB

main : add cli option to disable system prints (#1740) almost 2 years ago
whisper.h

30.2 kB

whisper : remove trailing whitespaces about 2 years ago