Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
91 commits
Select commit Hold shift + click to select a range
d6cc466
Get_Rows & Dequantize implementation adapted to work for repacked wei…
swetha097 Jun 3, 2025
994e02a
Resolve PR comments
swetha097 Jun 6, 2025
ed1d3a2
Get_Rows & Dequantize implementation adapted to work for repacked wei…
swetha097 Jun 3, 2025
6959d41
Resolve PR comments
swetha097 Jun 6, 2025
1a79d18
Merge branch 'swe_pr/get_rows' of https://github.com/swetha097/whispe…
swetha097 Jun 17, 2025
1e72e4b
Merge branch 'master' into swe_pr/get_rows
swetha097 Jun 17, 2025
066b47a
Add the Get_Rows & Dequantize implementation adapted to work for repa…
swetha097 Jun 18, 2025
b9e152d
Get_Rows & Dequantize implementation adapted to work for repacked wei…
swetha097 Jun 3, 2025
2705c08
Resolve PR comments
swetha097 Jun 6, 2025
70cf05a
Add the Get_Rows & Dequantize implementation adapted to work for repa…
swetha097 Jun 18, 2025
e53bb02
Merge branch 'swe_pr/get_rows_q4_K' of https://github.com/swetha097/w…
swetha097 Jun 19, 2025
3e65f51
android : update CMakeLists.txt to use FetchContent for ggml (#3268)
danbev Jun 19, 2025
1446e64
Remove q4_0 code implementation for get_rows & dequantize
swetha097 Jun 20, 2025
099aa24
Fix warning
swetha097 Jun 20, 2025
471df13
Add `ggml_roll` (ggml/1274)
Acly Jun 18, 2025
4fc9c34
ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)
chaxu01 Jun 18, 2025
34940ab
ggml-cpu: fix uncaught underscore terminators (llama/14023)
taronaeo Jun 18, 2025
203451b
ggml-cpu: reduce asm calls for hsum (llama/14037)
taronaeo Jun 18, 2025
b251d73
metal : add mean kernel (llama/14267)
ggerganov Jun 19, 2025
1aca7b5
Vulkan: Set device max size for host memory to avoid OOM warning and …
0cc4m Jun 19, 2025
be4ea08
llamafile : support s390x SIMD instruction set (llama/14273)
taronaeo Jun 19, 2025
a02a2d4
sycl: Cleanup codepaths in Get Rows in sycl backend (llama/14215)
ShanoToni Jun 19, 2025
cef59c1
build : suppress gcc15 compile warnings (llama/14261)
fanyang89 Jun 19, 2025
71adde9
ggml-cpu : remove unnecesary arm feature detection (llama/14281)
slaren Jun 19, 2025
5efd43c
CUDA: add conv_2d_dw (llama/14265)
am17an Jun 20, 2025
694f435
ggml: Update KleidiAI to v1.9.0 (llama/14277)
chaxu01 Jun 20, 2025
018b2d3
ggml : fix repack work size for mul_mat_id (llama/14292)
ggerganov Jun 20, 2025
33d1f0a
cuda : synchronize graph capture and cublas handle destruction (llama…
slaren Jun 20, 2025
af71681
Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)
ckastner Jun 20, 2025
a455dcb
sycl: add usage of enqueue_functions extension (llama/14244)
s-Nick Jun 20, 2025
b68222f
CUDA: add conv_2d_transpose (llama/14287)
am17an Jun 20, 2025
d65a579
sync : ggml
ggerganov Jun 20, 2025
e6c10cf
talk-llama : sync llama.cpp
ggerganov Jun 20, 2025
cead8f5
ruby : specify Apple frameworks explicitly on build (#3270)
KitaitiMakoto Jun 23, 2025
a422176
ci : add apt-get clean to musa Dockerfile (#3275)
danbev Jun 23, 2025
4d6ae52
command: output commands to text file (#3273)
aaron-ang Jun 24, 2025
a0d2c63
whisper : add .gitignore entries for OpenVINO support (#3276)
mochiya98 Jun 24, 2025
9c47902
ci : reduce musa image size (#3277)
danbev Jun 24, 2025
0083335
coreml : backport CoreML features to macos < 14 (#3255)
glaszig Jun 24, 2025
c85b1ae
bindings.java : update java example (#3281)
Jo4sDev Jun 25, 2025
7dd2997
ci : enable main-cuda build (#3282)
danbev Jun 25, 2025
1ad258c
stream : add nullptr check of whisper_context (#3283)
danbev Jun 25, 2025
dc8dda6
bench : print system info before ctx check
ggerganov Jun 25, 2025
06bdaa6
bench : update benches
ggerganov Jun 25, 2025
a8d002c
release : v1.7.6
ggerganov Jun 25, 2025
4daf705
ci : add support for tag-based releases (#3287)
danbev Jun 25, 2025
897b071
docs : add cmake "-j" flag in README.md (#3284)
toboil-features Jun 26, 2025
37303ab
Resolve minor PR comments
swetha097 Jun 26, 2025
a4e2602
Merge branch 'master' into swe_pr/q4_K_get_rows
swetha097 Jun 26, 2025
35034c5
ci : add should_release variable (#3288)
danbev Jun 26, 2025
32cf4e2
whisper : add version function (#3289)
danbev Jun 26, 2025
f8abbeb
ruby : add Whisper::VERSION (#3292)
KitaitiMakoto Jun 27, 2025
7069394
ci: set fail-fast to false in docker.yml (#3294)
danbev Jun 27, 2025
c88ffbf
ci : use selective copy for musa image (#3296)
danbev Jun 27, 2025
515df20
ggml-quants : rename best_mad to best_error (ggml/1283)
danbev Jun 24, 2025
9d7cb80
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
Acly Jul 1, 2025
c1418b9
metal : fix thread-safety (llama/14300)
ggerganov Jun 21, 2025
e036676
Add support for VK_EXT_debug_utils to add labels to Vulkan objects. (…
mtavenrath Jun 21, 2025
abb650c
CUDA: add mean operation (llama/14313)
am17an Jun 22, 2025
791201a
HIP: enable vec fattn on RDNA4 (llama/14323)
IMbackK Jun 22, 2025
06b01ba
CUDA: mul_mat_v support for batch sizes > 1 (llama/14262)
JohannesGaessler Jun 23, 2025
6a1d12a
CUDA/HIP: optimize mmv paths taken for HIP devices (llama/14324)
IMbackK Jun 23, 2025
acfbf29
opencl: ref count `ggml_backend_opencl_context` and refactor profilin…
lhez Jun 24, 2025
fc28594
sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (llam…
ShanoToni Jun 25, 2025
99764f5
ggml : do not output unprintable characters on GGUF load failure (lla…
CISC Jun 25, 2025
16aa7d1
ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)
taronaeo Jun 25, 2025
a5e6a3c
musa: enable fp16 mma (all) and cublas on qy2 (llama/13842)
yeahdongcn Jun 26, 2025
c848b9f
metal : batch rows copy in a single threadgroup (llama/14384)
ggerganov Jun 26, 2025
c300f1e
metal : add special-case mat-vec mul for ne00 == 4 (llama/14385)
ggerganov Jun 26, 2025
566462a
cmake: regen vulkan shaders when shaders-gen sources change (llama/14…
mtmcp Jun 26, 2025
48fb51f
ggml : add ggml_set_rows (llama/14274)
rgerganov Jun 27, 2025
0b09f5b
vulkan: Fix GGML_VULKAN_SHADER_DEBUG_INFO (llama/14427)
jeffbolznv Jun 28, 2025
f31ed38
fix async_mode bug (llama/14432)
bachelor-dou Jun 28, 2025
9e48afb
vulkan: lock accesses of pinned_memory vector (llama/14333)
jeffbolznv Jun 28, 2025
f641a4c
vulkan: handle noncontig in the final case of ggml_vk_get_cpy_pipelin…
jeffbolznv Jun 28, 2025
b900ee4
CUDA: add bf16 and f32 support to cublas_mul_mat_batched (llama/14361)
am17an Jun 28, 2025
00b3623
vulkan: Add fusion support for RMS_NORM+MUL (llama/14366)
jeffbolznv Jun 29, 2025
8bc638e
ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158)
CISC Jun 29, 2025
130044f
ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (llama/14443)
CISC Jun 29, 2025
e81be92
SYCL: disable faulty fp16 exp kernel (llama/14395)
qnixsynapse Jun 29, 2025
3239359
scripts : make the shell scripts cross-platform (llama/14341)
vedranmiletic Jun 30, 2025
6bb1234
cmake : Remove redundant include path in CMakeLists.txt (llama/14452)
xiaobing318 Jun 30, 2025
e29e36a
ggml-cpu: sycl: Re-enable exp f16 (llama/14462)
Rbiessy Jun 30, 2025
679f31a
metal : disable fast-math for some cpy kernels (llama/14460)
ggerganov Jun 30, 2025
b5b237d
Add Conv2d for CPU (llama/14388)
am17an Jun 30, 2025
1e930ab
opencl : add GEGLU, REGLU, SWIGLU (llama/14456)
lhez Jul 1, 2025
c4ea72b
ggml : remove trailing whitespace (llama/0)
ggerganov Jul 1, 2025
1f816de
talk-llama : sync llama.cpp
ggerganov Jul 1, 2025
bca021c
sync : ggml
ggerganov Jul 1, 2025
d9999d5
feat: support vad for addon.node (#3301)
buxuku Jul 2, 2025
74bc3c6
Merge remote-tracking branch 'origin/master' into swe_pr/q4_K_get_rows
swetha097 Jul 3, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions .devops/main-cuda.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}

RUN apt-get update && \
apt-get install -y build-essential libsdl2-dev wget cmake git \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

# Ref: https://stackoverflow.com/a/53464012
Expand All @@ -26,15 +27,24 @@ COPY .. .
# Enable cuBLAS
RUN make base.en CMAKE_ARGS="-DGGML_CUDA=1"

RUN find /app/build -name "*.o" -delete && \
find /app/build -name "*.a" -delete && \
rm -rf /app/build/CMakeFiles && \
rm -rf /app/build/cmake_install.cmake && \
rm -rf /app/build/_deps

FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
ENV CUDA_MAIN_VERSION=12.3
ENV LD_LIBRARY_PATH /usr/local/cuda-${CUDA_MAIN_VERSION}/compat:$LD_LIBRARY_PATH
WORKDIR /app

RUN apt-get update && \
apt-get install -y curl ffmpeg wget cmake git \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*

COPY --from=build /app /app
RUN du -sh /app/*
RUN find /app -type f -size +100M
ENV PATH=/app/build/bin:$PATH
ENTRYPOINT [ "bash", "-c" ]
21 changes: 16 additions & 5 deletions .devops/main-musa.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -10,20 +10,31 @@ FROM ${BASE_MUSA_DEV_CONTAINER} AS build
WORKDIR /app

RUN apt-get update && \
apt-get install -y build-essential libsdl2-dev wget cmake git \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
apt-get install -y build-essential libsdl2-dev wget cmake git && \
apt-get clean && \
rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/* /tmp/* /var/tmp/*

COPY .. .
# Enable muBLAS
RUN make base.en CMAKE_ARGS="-DGGML_MUSA=1"

RUN find /app/build -name "*.o" -delete && \
find /app/build -name "*.a" -delete && \
rm -rf /app/build/CMakeFiles && \
rm -rf /app/build/cmake_install.cmake && \
rm -rf /app/build/_deps

FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
WORKDIR /app

RUN apt-get update && \
apt-get install -y curl ffmpeg wget cmake git \
&& rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
apt-get install -y curl ffmpeg wget cmake git && \
apt-get clean && \
rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/* /tmp/* /var/tmp/*

COPY --from=build /app/build/bin /app/build/bin
COPY --from=build /app/samples /app/samples
COPY --from=build /app/models /app/models

COPY --from=build /app /app
ENV PATH=/app/build/bin:$PATH
ENTRYPOINT [ "bash", "-c" ]
48 changes: 29 additions & 19 deletions .github/workflows/build.yml
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ on:
push:
branches:
- master
tags:
- 'v*'
pull_request:
types: [opened, synchronize, reopened]
workflow_dispatch:
Expand Down Expand Up @@ -41,6 +43,7 @@ jobs:
runs-on: ubuntu-latest
outputs:
tag_name: ${{ steps.tag.outputs.name }}
should_release: ${{ steps.tag.outputs.should_release }}

steps:
- name: Checkout with full history
Expand All @@ -55,28 +58,42 @@ jobs:
BUILD_NUMBER=$(git rev-list --count HEAD)
SHORT_HASH=$(git rev-parse --short=7 HEAD)
CUSTOM_TAG="${{ github.event.inputs.pre_release_tag }}"
SHOULD_RELEASE="false"

echo "Raw values:"
echo "BUILD_NUMBER: $BUILD_NUMBER"
echo "SHORT_HASH: $SHORT_HASH"
echo "BRANCH_NAME: ${{ env.BRANCH_NAME }}"
echo "CUSTOM_TAG: $CUSTOM_TAG"

# Use custom tag if provided
if [[ -n "$CUSTOM_TAG" ]]; then
if [[ "${{ github.ref_type }}" == "tag" ]]; then
echo "Using pushed tag name"
TAG_NAME="${{ github.ref_name }}"
SHOULD_RELEASE="true"
elif [[ -n "$CUSTOM_TAG" ]]; then
echo "Using custom tag"
TAG_NAME="${CUSTOM_TAG}"
SHOULD_RELEASE="true"
elif [[ "${{ github.event.inputs.create_release }}" == "true" ]]; then
echo "Manual release requested"
SHOULD_RELEASE="true"
TAG_NAME="b${BUILD_NUMBER}"
elif [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
echo "Using master branch format"
TAG_NAME="b${BUILD_NUMBER}"
SHOULD_RELEASE="false"
else
echo "Using non-master branch format"
SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
TAG_NAME="${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}"
SHOULD_RELEASE="false"
fi

echo "Final tag name: $TAG_NAME"
echo "Should release: $SHOULD_RELEASE"
echo "name=$TAG_NAME" >> $GITHUB_OUTPUT
echo "should_release=$SHOULD_RELEASE" >> $GITHUB_OUTPUT


ubuntu-22:
if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' ||
Expand Down Expand Up @@ -579,6 +596,7 @@ jobs:
if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' ||
github.event.inputs.run_type == 'full-ci' }}
runs-on: windows-latest
needs: determine-tag

strategy:
matrix:
Expand Down Expand Up @@ -662,9 +680,7 @@ jobs:
Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-bin-${{ matrix.arch }}.zip"

- name: Upload binaries
if: matrix.sdl2 == 'ON' && ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
if: matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }}
uses: actions/upload-artifact@v4
with:
name: whisper-bin-${{ matrix.arch }}.zip
Expand Down Expand Up @@ -750,9 +766,7 @@ jobs:
Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-blas-bin-${{ matrix.arch }}.zip"

- name: Upload binaries
if: matrix.blas == 'ON' && matrix.sdl2 == 'ON' && ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
if: matrix.blas == 'ON' && matrix.sdl2 == 'ON' && ${{ needs.determine-tag.outputs.should_release }}
uses: actions/upload-artifact@v4
with:
name: whisper-blas-bin-${{ matrix.arch }}.zip
Expand All @@ -762,6 +776,7 @@ jobs:
if: ${{ github.event_name == 'push' || github.event_name == 'pull_request' ||
github.event.inputs.run_type == 'full-ci' }}
runs-on: windows-2022
needs: determine-tag
strategy:
fail-fast: false
matrix:
Expand Down Expand Up @@ -960,9 +975,7 @@ jobs:
Compress-Archive -Path "build/bin/${{ matrix.build }}" -DestinationPath "whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip"

- name: Upload binaries
if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
if: ${{ needs.determine-tag.outputs.should_release }}
uses: actions/upload-artifact@v4
with:
name: whisper-cublas-${{ matrix.cuda-toolkit }}-bin-${{ matrix.arch }}.zip
Expand Down Expand Up @@ -1039,16 +1052,11 @@ jobs:

- name: Pack artifacts
id: pack_artifacts
if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
run: |
zip --symlinks -r whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip build-apple/whisper.xcframework

- name: Upload artifacts
if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
if: ${{ needs.determine-tag.outputs.should_release }}
uses: actions/upload-artifact@v4
with:
path: whisper-${{ needs.determine-tag.outputs.tag_name }}-xcframework.zip
Expand Down Expand Up @@ -1226,7 +1234,7 @@ jobs:
./build/bin/quantize models/ggml-tiny.en.bin models/ggml-tiny.en-q4_0.bin q4_0

release:
if: ${{ github.event.inputs.create_release == 'true' || github.event.inputs.pre_release_tag != '' }}
if: ${{ github.event.inputs.create_release == 'true' || github.event.inputs.pre_release_tag != '' || startsWith(github.ref, 'refs/tags/v') }}

runs-on: ubuntu-latest

Expand Down Expand Up @@ -1269,6 +1277,7 @@ jobs:
with:
tag_name: ${{ needs.determine-tag.outputs.tag_name }}
prerelease: ${{ github.event.inputs.pre_release_tag != '' }}
draft: true

- name: Upload release
id: upload_release
Expand All @@ -1295,7 +1304,8 @@ jobs:
coreml-base-en:
if: ${{ (github.event_name == 'push' && github.ref == 'refs/heads/master') ||
github.event.inputs.create_release == 'true' ||
github.event.inputs.pre_release_tag != '' }}
github.event.inputs.pre_release_tag != '' ||
startsWith(github.ref, 'refs/tags/v') }}
runs-on: macos-latest
needs: determine-tag

Expand Down
41 changes: 27 additions & 14 deletions .github/workflows/docker.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,14 +15,13 @@ jobs:
env:
COMMIT_SHA: ${{ github.sha }}
strategy:
fail-fast: false
matrix:
config:
- { tag: "main", dockerfile: ".devops/main.Dockerfile", platform: "linux/amd64" }
- { tag: "main-musa", dockerfile: ".devops/main-musa.Dockerfile", platform: "linux/amd64" }
- { tag: "main-intel", dockerfile: ".devops/main-intel.Dockerfile", platform: "linux/amd64" }
#TODO: the cuda image keeps failing - disable for now
# https://github.com/ggerganov/whisper.cpp/actions/runs/11019444428/job/30602020339
#- { tag: "main-cuda", dockerfile: ".devops/main-cuda.Dockerfile", platform: "linux/amd64" }
- { tag: "main-cuda", dockerfile: ".devops/main-cuda.Dockerfile", platform: "linux/amd64" }

steps:
- name: Check out the repo
Expand All @@ -43,21 +42,35 @@ jobs:
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Build and push Docker image (versioned)
if: github.event_name == 'push'
uses: docker/build-push-action@v5
with:
context: .
push: true
platforms: ${{ matrix.config.platform }}
tags: "ghcr.io/${{ github.repository }}:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}"
file: ${{ matrix.config.dockerfile }}
- name: Free up disk space
run: |
sudo apt-get remove -y '^dotnet-.*' '^llvm-.*' '^mysql-.*' '^postgresql-.*'
sudo apt-get autoremove -y
sudo apt-get autoclean

sudo rm -rf /usr/share/dotnet
sudo rm -rf /usr/local/lib/android
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL

docker system prune -af

df -h

- name: Generate tags
id: tags
run: |
TAGS="ghcr.io/${{ github.repository }}:${{ matrix.config.tag }}"
if [ "${{ github.event_name }}" == "push" ]; then
TAGS="$TAGS,ghcr.io/${{ github.repository }}:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}"
fi
echo "tags=$TAGS" >> $GITHUB_OUTPUT

- name: Build and push Docker image (tagged)
uses: docker/build-push-action@v4
uses: docker/build-push-action@v5
with:
context: .
push: ${{ github.event_name == 'push' }}
platforms: ${{ matrix.config.platform }}
tags: "ghcr.io/${{ github.repository }}:${{ matrix.config.tag }}"
tags: ${{ steps.tags.outputs.tags }}
file: ${{ matrix.config.dockerfile }}
2 changes: 2 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,8 @@ extra/bench-gg.txt
models/*.mlmodel
models/*.mlmodelc
models/*.mlpackage
models/*-encoder-openvino.xml
models/*-encoder-openvino-cache/
bindings/java/.gradle/
bindings/java/.idea/
.idea/
Expand Down
6 changes: 5 additions & 1 deletion CMakeLists.txt
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
cmake_minimum_required(VERSION 3.5) # for add_link_options and implicit target directories.
project("whisper.cpp" C CXX)
project("whisper.cpp" VERSION 1.7.5)
project("whisper.cpp" VERSION 1.7.6)
include(CheckIncludeFileCXX)

set(SOVERSION 1)
Expand Down Expand Up @@ -178,6 +178,10 @@ get_directory_property(WHISPER_TRANSIENT_DEFINES COMPILE_DEFINITIONS)
set_target_properties(whisper PROPERTIES PUBLIC_HEADER ${CMAKE_CURRENT_SOURCE_DIR}/include/whisper.h)
install(TARGETS whisper LIBRARY PUBLIC_HEADER)

target_compile_definitions(whisper PRIVATE
WHISPER_VERSION="${PROJECT_VERSION}"
)

configure_package_config_file(
${CMAKE_CURRENT_SOURCE_DIR}/cmake/whisper-config.cmake.in
${CMAKE_CURRENT_BINARY_DIR}/whisper-config.cmake
Expand Down
14 changes: 8 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
[![Conan Center](https://shields.io/conan/v/whisper-cpp)](https://conan.io/center/whisper-cpp)
[![npm](https://img.shields.io/npm/v/whisper.cpp.svg)](https://www.npmjs.com/package/whisper.cpp/)

Stable: [v1.7.5](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.5) / [Roadmap](https://github.com/orgs/ggml-org/projects/4/)
Stable: [v1.7.6](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.6) / [Roadmap](https://github.com/orgs/ggml-org/projects/4/)

High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model:

Expand Down Expand Up @@ -80,7 +80,7 @@ Now build the [whisper-cli](examples/cli) example and transcribe an audio file l
```bash
# build the project
cmake -B build
cmake --build build --config Release
cmake --build build -j --config Release

# transcribe an audio file
./build/bin/whisper-cli -f samples/jfk.wav
Expand Down Expand Up @@ -149,7 +149,7 @@ standard cmake setup with:
```bash
# build with GGML_BLAS defined
cmake -B build -DGGML_BLAS=1
cmake --build build --config Release
cmake --build build -j --config Release
./build/bin/whisper-cli [ .. etc .. ]
```

Expand All @@ -163,7 +163,7 @@ Here are the steps for creating and using a quantized model:
```bash
# quantize a model with Q5_0 method
cmake -B build
cmake --build build --config Release
cmake --build build -j --config Release
./build/bin/quantize models/ggml-base.en.bin models/ggml-base.en-q5_0.bin q5_0

# run the examples as usual, specifying the quantized model file
Expand Down Expand Up @@ -489,7 +489,7 @@ You will need to have [sdl2](https://wiki.libsdl.org/SDL2/Installation) installe

```bash
cmake -B build -DWHISPER_SDL2=ON
cmake --build build --config Release
cmake --build build -j --config Release
./build/bin/whisper-stream -m ./models/ggml-base.en.bin -t 8 --step 500 --length 5000
```

Expand Down Expand Up @@ -709,7 +709,9 @@ For more details, see the conversion script [models/convert-pt-to-ggml.py](model
## XCFramework
The XCFramework is a precompiled version of the library for iOS, visionOS, tvOS,
and macOS. It can be used in Swift projects without the need to compile the
library from source. For examples:
library from source. For example, the v1.7.5 version of the XCFramework can be
used as follows:

```swift
// swift-tools-version: 5.10
// The swift-tools-version declares the minimum version of Swift required to build this package.
Expand Down
Loading
Loading