mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-04 23:06:22 -04:00
13734ae9fa
feat(backend): Add Sherpa ONNX backend and Omnilingual ASR Adds a new Go backend wrapping sherpa-onnx via purego (no cgo). Same approach as opus/stablediffusion-ggml/whisper — a thin C shim (csrc/shim.c + shim.h → libsherpa-shim.so) wraps the bits purego can't reach directly: nested struct config writes, result-struct field reads, and the streaming TTS callback trampoline. The Go side uses opaque uintptr handles and purego.NewCallback for the TTS callback. Supports: - VAD via sherpa-onnx's Silero VAD - Offline ASR: Whisper, Paraformer, SenseVoice, Omnilingual CTC - Online/streaming ASR: zipformer transducer with endpoint detection (AudioTranscriptionStream emits delta events during decode) - Offline TTS: VITS (LJS, etc.) - Streaming TTS: sherpa-onnx's callback API → PCM chunks on a channel, prefixed by a streaming WAV header Gallery entries: omnilingual-0.3b-ctc-q8-sherpa (1600-language offline ASR), streaming-zipformer-en-sherpa (low-latency streaming ASR), silero-vad-sherpa, vits-ljs-sherpa. E2E coverage: tests/e2e-backends for offline + streaming ASR, tests/e2e for the full realtime pipeline (VAD + STT + TTS). Assisted-by: claude-opus-4-7-1M [Claude Code] Signed-off-by: Richard Palethorpe <io@richiejp.com>
121 lines
4.2 KiB
Makefile
121 lines
4.2 KiB
Makefile
CURRENT_DIR=$(abspath ./)
|
|
GOCMD=go
|
|
|
|
ONNX_VERSION?=1.24.4
|
|
# v1.12.39 — includes upstream's onnxruntime 1.24.4 bump (#3501). Earlier
|
|
# pinned commits only support onnxruntime 1.23.2, which has no CUDA 13
|
|
# pre-built tarball, blocking the -gpu-nvidia-cuda-13 build matrix entry.
|
|
SHERPA_COMMIT?=7288d15e3e31a7bd589b2ba88828d521e7a6b140
|
|
ONNX_ARCH?=x64
|
|
ONNX_OS?=linux
|
|
|
|
ifneq (,$(findstring aarch64,$(shell uname -m)))
|
|
ONNX_ARCH=aarch64
|
|
endif
|
|
|
|
ifeq ($(OS),Darwin)
|
|
ONNX_OS=osx
|
|
ifneq (,$(findstring aarch64,$(shell uname -m)))
|
|
ONNX_ARCH=arm64
|
|
else ifneq (,$(findstring arm64,$(shell uname -m)))
|
|
ONNX_ARCH=arm64
|
|
else
|
|
ONNX_ARCH=x86_64
|
|
endif
|
|
endif
|
|
|
|
# Upstream onnxruntime ships CUDA 12 and CUDA 13 variants under different
|
|
# names: -gpu-<ver>.tgz for CUDA 12, -gpu_cuda13-<ver>.tgz for CUDA 13
|
|
# (note underscore vs dash). CUDA 13 tarballs only exist from 1.24.x onward.
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
SHERPA_GPU=ON
|
|
ONNX_PROVIDER=cuda
|
|
ifeq ($(CUDA_MAJOR_VERSION),13)
|
|
ONNX_VARIANT=-gpu_cuda13
|
|
else
|
|
ONNX_VARIANT=-gpu
|
|
endif
|
|
else
|
|
ONNX_VARIANT=
|
|
SHERPA_GPU=OFF
|
|
ONNX_PROVIDER=cpu
|
|
endif
|
|
|
|
JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
|
|
|
|
sources/onnxruntime:
|
|
mkdir -p sources/onnxruntime
|
|
curl -L https://github.com/microsoft/onnxruntime/releases/download/v$(ONNX_VERSION)/onnxruntime-$(ONNX_OS)-$(ONNX_ARCH)$(ONNX_VARIANT)-$(ONNX_VERSION).tgz \
|
|
-o sources/onnxruntime/onnxruntime.tgz
|
|
cd sources/onnxruntime && tar -xf onnxruntime.tgz --strip-components=1 && rm onnxruntime.tgz
|
|
|
|
sources/sherpa-onnx: sources/onnxruntime
|
|
git clone https://github.com/k2-fsa/sherpa-onnx.git sources/sherpa-onnx
|
|
cd sources/sherpa-onnx && git checkout $(SHERPA_COMMIT)
|
|
mkdir -p sources/sherpa-onnx/build
|
|
# sherpa-onnx's cmake detects a pre-installed onnxruntime via the
|
|
# SHERPA_ONNXRUNTIME_{INCLUDE,LIB}_DIR env vars (not via -D flags).
|
|
# Point them at our locally-downloaded Microsoft tarball — without
|
|
# this, sherpa-onnx falls through to download_onnxruntime() which
|
|
# fetches from csukuangfj/onnxruntime-libs. For the GPU 1.24.4
|
|
# build that release mirror publishes `-patched.zip` instead of the
|
|
# expected `.tgz`, so the download 404s and the build fails.
|
|
cd sources/sherpa-onnx/build && \
|
|
SHERPA_ONNXRUNTIME_INCLUDE_DIR=$(CURRENT_DIR)/sources/onnxruntime/include \
|
|
SHERPA_ONNXRUNTIME_LIB_DIR=$(CURRENT_DIR)/sources/onnxruntime/lib \
|
|
cmake \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DCMAKE_C_FLAGS="-Wno-error=format-security" \
|
|
-DCMAKE_CXX_FLAGS="-Wno-error=format-security" \
|
|
-DSHERPA_ONNX_ENABLE_GPU=$(SHERPA_GPU) \
|
|
-DSHERPA_ONNX_ENABLE_TTS=ON \
|
|
-DSHERPA_ONNX_ENABLE_BINARY=OFF \
|
|
-DSHERPA_ONNX_ENABLE_PYTHON=OFF \
|
|
-DSHERPA_ONNX_ENABLE_TESTS=OFF \
|
|
-DSHERPA_ONNX_ENABLE_C_API=ON \
|
|
-DBUILD_SHARED_LIBS=ON \
|
|
-DSHERPA_ONNX_USE_PRE_INSTALLED_ONNXRUNTIME_IF_AVAILABLE=ON \
|
|
..
|
|
cd sources/sherpa-onnx/build && make -j$(JOBS)
|
|
|
|
backend-assets/lib: sources/sherpa-onnx sources/onnxruntime
|
|
mkdir -p backend-assets/lib
|
|
cp -rfLv sources/onnxruntime/lib/* backend-assets/lib/
|
|
cp -rfLv sources/sherpa-onnx/build/lib/*.so* backend-assets/lib/ 2>/dev/null || true
|
|
cp -rfLv sources/sherpa-onnx/build/lib/*.dylib backend-assets/lib/ 2>/dev/null || true
|
|
|
|
# libsherpa-shim wraps sherpa-onnx's nested config structs and TTS
|
|
# callback plumbing behind a purego-friendly API: opaque handles plus
|
|
# fixed-signature setters/getters/trampoline. Plain C compile — no cgo.
|
|
SHIM_EXT=so
|
|
ifeq ($(OS),Darwin)
|
|
SHIM_EXT=dylib
|
|
endif
|
|
|
|
backend-assets/lib/libsherpa-shim.$(SHIM_EXT): csrc/shim.c csrc/shim.h backend-assets/lib
|
|
$(CC) -shared -fPIC -O2 \
|
|
-I$(CURRENT_DIR)/sources/sherpa-onnx/sherpa-onnx/c-api \
|
|
-o $@ csrc/shim.c \
|
|
-L$(CURRENT_DIR)/backend-assets/lib \
|
|
-lsherpa-onnx-c-api \
|
|
-Wl,-rpath,'$$ORIGIN'
|
|
|
|
sherpa-onnx: backend-assets/lib backend-assets/lib/libsherpa-shim.$(SHIM_EXT)
|
|
CGO_ENABLED=0 $(GOCMD) build \
|
|
-ldflags "$(LD_FLAGS) -X main.onnxProvider=$(ONNX_PROVIDER)" \
|
|
-tags "$(GO_TAGS)" -o sherpa-onnx ./
|
|
|
|
package:
|
|
bash package.sh
|
|
|
|
build: sherpa-onnx package
|
|
|
|
clean:
|
|
rm -rf sherpa-onnx sources/ backend-assets/ package/ vits-ljs/ sherpa-onnx-whisper-*/
|
|
|
|
test: sherpa-onnx
|
|
LD_LIBRARY_PATH=$(CURRENT_DIR)/backend-assets/lib \
|
|
bash test.sh
|
|
|
|
.PHONY: build package clean test
|