You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* tag 'v1.7.4': (32 commits)
release : v1.7.4
ci : cont
ci : fix ubuntu runner names
cli : fix segfault on missing argument (ggml-org#2700)
ci : fix arm builds
sync : ggml
ggml : do not install metal source when embed library (ggml/1054)
metal : avoid uint (llama/11019)
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (llama/11027)
vulkan: optimize mul_mat for small values of N (llama/10991)
vulkan: im2col and matmul optimizations for stable diffusion (llama/10942)
vulkan: Use push constant offset to handle misaligned descriptors (llama/10987)
vulkan: multi-row k quants (llama/10846)
examples, ggml : fix GCC compiler warnings (llama/10983)
ggml : more perfo with llamafile tinyblas on x86_64 (llama/10714)
ggml : use wstring for backend search paths (llama/10960)
ggml : fix arm enabled features check (llama/10961)
ggml : fix const usage in SSE path (llama/10962)
ggml : fix run-time on FreeBSD in get_executable_path() (llama/10948)
vulkan: build fixes for 32b (llama/10927)
...
High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model:
13
13
@@ -293,7 +293,7 @@ This can result in significant speedup in encoder performance. Here are the inst
293
293
The first time run on an OpenVINO device is slow, since the OpenVINO framework will compile the IR (Intermediate Representation) model to a device-specific 'blob'. This device-specific blob will get
294
294
cached for the next run.
295
295
296
-
For more information about the Core ML implementation please refer to PR [#1037](https://github.com/ggerganov/whisper.cpp/pull/1037).
296
+
For more information about the OpenVINO implementation please refer to PR [#1037](https://github.com/ggerganov/whisper.cpp/pull/1037).
297
297
298
298
## NVIDIA GPU support
299
299
@@ -381,9 +381,9 @@ The [stream](examples/stream) tool samples the audio every half a second and run
381
381
More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/issues/10).
0 commit comments