mirror of
https://github.com/mudler/LocalAI
synced 2026-05-24 09:28:23 +00:00
a8d7d37a3c
* fix(docs): correct broken Hugo relrefs
The Hugo build has been failing on master since the relevant pages
landed:
- text-generation.md:720 referenced `/docs/features/distributed-mode`,
but Hugo `relref` paths are relative to the content root, not the
rendered URL. Drop the `/docs/` prefix so the lookup matches the
existing `features/...` form used elsewhere in the file.
- audio-transform.md:144 referenced `tts.md`; the actual page is
`text-to-audio.md`.
Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(kokoros): stub Diarize and AudioTransform Backend trait methods
The recent backend.proto additions (Diarize, AudioTransform,
AudioTransformStream) extended the gRPC Backend trait, breaking
kokoros-grpc compilation with E0046 because the Rust implementation
hadn't picked up the new methods. Add Unimplemented stubs matching the
existing pattern for non-applicable RPCs in this TTS-only backend.
Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(vibevoice-cpp): track upstream ABI + wire 1.5B voice cloning
Two recent commits in mudler/vibevoice.cpp reshaped the vv_capi_tts
signature without a corresponding bump on the LocalAI side:
3bd759c "1.5b: unify into a single tts entry point" inserted a
ref_audio_path parameter between voice_path and dst_wav_path.
ad856bd "1.5b: multi-speaker dialog support" promoted that to a
(const char* const* ref_audio_paths, int n_ref_audio_paths)
pair for per-speaker conditioning.
Because purego resolves symbols by name and not by signature, the
build kept linking; at runtime the misaligned arguments turned the
TTS->ASR closed-loop test into a SIGSEGV inside cgo. Track HEAD
explicitly and bring the bridge in line with it:
* Update the CppTTS purego binding to the 9-arg form. purego
marshals []*byte as a **char by handing the C side the underlying
array address; nil/empty maps to NULL, which matches the C
contract for "no reference audio" on the realtime-0.5B path.
* Add a `ref_audio` gallery option (comma-separated, repeatable)
that the 1.5B path consumes for runtime voice cloning. Multiple
entries are interpreted as one WAV per speaker (Speaker 0..n-1).
* TTSRequest.Voice now routes by extension/shape: `.wav` or a
comma-separated list goes to ref_audio_paths; anything else stays
on voice_path (realtime-0.5B's pre-baked voice gguf).
* Pin VIBEVOICE_CPP_VERSION to ad856bd and wire the Makefile into
the existing bump_deps matrix so future upstream rolls land as
reviewable PRs instead of a silent CI break.
Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* refactor(vibevoice-cpp): use ModelOptions.AudioPath for 1.5B ref audio
Use the existing audio_path field from ModelOptions (already plumbed
through config_file's `audio_path:` YAML and consumed by other audio
backends like kokoros) instead of inventing a custom `ref_audio:`
Options[] string. Multi-speaker setups stay on a single comma-
separated value.
No behavior change beyond the gallery key name; per-call routing via
TTSRequest.Voice is unchanged.
Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
131 lines
4.4 KiB
Makefile
131 lines
4.4 KiB
Makefile
CMAKE_ARGS?=
|
|
BUILD_TYPE?=
|
|
NATIVE?=false
|
|
|
|
GOCMD?=go
|
|
GO_TAGS?=
|
|
JOBS?=$(shell nproc --ignore=1)
|
|
|
|
# vibevoice.cpp version. Pinned to a commit hash and auto-bumped by
|
|
# .github/workflows/bump_deps.yaml (the matrix entry mirrors what we
|
|
# already do for ik_llama.cpp / llama.cpp / whisper.cpp). Floating on
|
|
# `master` led to silent ABI breaks reaching CI — pin it.
|
|
VIBEVOICE_REPO?=https://github.com/mudler/vibevoice.cpp
|
|
VIBEVOICE_CPP_VERSION?=ad856bda6b1311b7f3d7c4a667be43eeb8a8249a
|
|
SO_TARGET?=libgovibevoicecpp.so
|
|
|
|
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
|
|
CMAKE_ARGS+=-DVIBEVOICE_BUILD_TESTS=OFF
|
|
CMAKE_ARGS+=-DVIBEVOICE_BUILD_EXAMPLES=OFF
|
|
|
|
ifeq ($(NATIVE),false)
|
|
CMAKE_ARGS+=-DGGML_NATIVE=OFF
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS+=-DGGML_CUDA=ON -DVIBEVOICE_GGML_CUDA=ON
|
|
else ifeq ($(BUILD_TYPE),openblas)
|
|
CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
|
|
else ifeq ($(BUILD_TYPE),clblas)
|
|
CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
|
|
else ifeq ($(BUILD_TYPE),hipblas)
|
|
CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DVIBEVOICE_GGML_HIPBLAS=ON
|
|
else ifeq ($(BUILD_TYPE),vulkan)
|
|
CMAKE_ARGS+=-DGGML_VULKAN=ON -DVIBEVOICE_GGML_VULKAN=ON
|
|
else ifeq ($(OS),Darwin)
|
|
ifneq ($(BUILD_TYPE),metal)
|
|
CMAKE_ARGS+=-DGGML_METAL=OFF
|
|
else
|
|
CMAKE_ARGS+=-DGGML_METAL=ON -DVIBEVOICE_GGML_METAL=ON
|
|
CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
|
|
endif
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),sycl_f16)
|
|
CMAKE_ARGS+=-DGGML_SYCL=ON \
|
|
-DCMAKE_C_COMPILER=icx \
|
|
-DCMAKE_CXX_COMPILER=icpx \
|
|
-DGGML_SYCL_F16=ON
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),sycl_f32)
|
|
CMAKE_ARGS+=-DGGML_SYCL=ON \
|
|
-DCMAKE_C_COMPILER=icx \
|
|
-DCMAKE_CXX_COMPILER=icpx
|
|
endif
|
|
|
|
sources/vibevoice.cpp:
|
|
mkdir -p sources/vibevoice.cpp
|
|
cd sources/vibevoice.cpp && \
|
|
git init && \
|
|
git remote add origin $(VIBEVOICE_REPO) && \
|
|
git fetch origin && \
|
|
git checkout $(VIBEVOICE_CPP_VERSION) && \
|
|
git submodule update --init --recursive --depth 1 --single-branch
|
|
|
|
# Detect OS
|
|
UNAME_S := $(shell uname -s)
|
|
|
|
# Only build CPU variants on Linux
|
|
ifeq ($(UNAME_S),Linux)
|
|
VARIANT_TARGETS = libgovibevoicecpp-avx.so libgovibevoicecpp-avx2.so libgovibevoicecpp-avx512.so libgovibevoicecpp-fallback.so
|
|
else
|
|
# On non-Linux (e.g., Darwin), build only fallback variant
|
|
VARIANT_TARGETS = libgovibevoicecpp-fallback.so
|
|
endif
|
|
|
|
vibevoice-cpp: main.go govibevoicecpp.go $(VARIANT_TARGETS)
|
|
CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o vibevoice-cpp ./
|
|
|
|
package: vibevoice-cpp
|
|
bash package.sh
|
|
|
|
build: package
|
|
|
|
clean: purge
|
|
rm -rf libgovibevoicecpp*.so package sources/vibevoice.cpp vibevoice-cpp
|
|
|
|
purge:
|
|
rm -rf build*
|
|
|
|
# Variants must build sequentially
|
|
.NOTPARALLEL:
|
|
|
|
# Build all variants (Linux only)
|
|
ifeq ($(UNAME_S),Linux)
|
|
libgovibevoicecpp-avx.so: sources/vibevoice.cpp
|
|
$(info ${GREEN}I vibevoice-cpp build info:avx${RESET})
|
|
SO_TARGET=libgovibevoicecpp-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
|
|
rm -rf build-libgovibevoicecpp-avx.so
|
|
|
|
libgovibevoicecpp-avx2.so: sources/vibevoice.cpp
|
|
$(info ${GREEN}I vibevoice-cpp build info:avx2${RESET})
|
|
SO_TARGET=libgovibevoicecpp-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgovibevoicecpp-custom
|
|
rm -rf build-libgovibevoicecpp-avx2.so
|
|
|
|
libgovibevoicecpp-avx512.so: sources/vibevoice.cpp
|
|
$(info ${GREEN}I vibevoice-cpp build info:avx512${RESET})
|
|
SO_TARGET=libgovibevoicecpp-avx512.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgovibevoicecpp-custom
|
|
rm -rf build-libgovibevoicecpp-avx512.so
|
|
endif
|
|
|
|
# Build fallback variant (all platforms)
|
|
libgovibevoicecpp-fallback.so: sources/vibevoice.cpp
|
|
$(info ${GREEN}I vibevoice-cpp build info:fallback${RESET})
|
|
SO_TARGET=libgovibevoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
|
|
rm -rf build-libgovibevoicecpp-fallback.so
|
|
|
|
libgovibevoicecpp-custom: CMakeLists.txt cpp/govibevoicecpp.cpp cpp/govibevoicecpp.h
|
|
mkdir -p build-$(SO_TARGET) && \
|
|
cd build-$(SO_TARGET) && \
|
|
cmake .. $(CMAKE_ARGS) && \
|
|
cmake --build . --config Release -j$(JOBS) --target govibevoicecpp && \
|
|
cd .. && \
|
|
mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET)
|
|
|
|
test: vibevoice-cpp
|
|
@echo "Running vibevoice-cpp tests..."
|
|
bash test.sh
|
|
@echo "vibevoice-cpp tests completed."
|
|
|
|
all: vibevoice-cpp package
|