mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
Adds result_map, the engine-to-proto boundary, and wires the offline transcription RPC. The handler branches on the ROUTED task: for Asr the request's prompt is whisper-style decoding context and becomes a request option, for Alignment the same field IS the transcript to align and becomes the text input. Routing has already decided which. The result text is TaskResult.text_output verbatim and is never derived from the segments. audio.cpp carries transcript text in text_output and nowhere else, so deriving it returns an empty transcript for every producer that reports segments without word timing. transcript_assembly already enforces that; this commit's job is not to undo it at the proto boundary, and result_map_ctest pins it there. read_audio_file now takes the sample rate the caller needs. Both file-fed speech handlers ask for 16 kHz mono, for two reasons: silero_vad and sortformer_diar refuse anything else outright, which turned an ordinary 44.1 kHz upload into INTERNAL, and nemotron_asr emits word timestamps in its own 16 kHz feature domain whatever the input was, so only a 16 kHz buffer makes the emitted nanoseconds right. Zero keeps the file's native rate and channels, which is what source separation will need. LoadedModel::check_can_serve answers a capability refusal before the lane is taken and before the input file is read. Routing is a pure read of the immutable capabilities, so a model that cannot serve an RPC no longer waits out somebody else's run to say so. VAD and Diarize use it too. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
191 lines
7.7 KiB
CMake
191 lines
7.7 KiB
CMake
cmake_minimum_required(VERSION 3.20)
|
|
project(audio-cpp-grpc-server LANGUAGES C CXX)
|
|
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
|
set(TARGET grpc-server)
|
|
|
|
set(AUDIO_CPP_DIR "${CMAKE_CURRENT_SOURCE_DIR}/audio.cpp"
|
|
CACHE PATH "Path to the pinned audio.cpp checkout")
|
|
option(AUDIO_CPP_GRPC_BUILD_TESTS "Build engine-linked ctest binaries" OFF)
|
|
|
|
if(NOT EXISTS "${AUDIO_CPP_DIR}/CMakeLists.txt")
|
|
message(FATAL_ERROR
|
|
"AUDIO_CPP_DIR does not contain an audio.cpp checkout: ${AUDIO_CPP_DIR}. "
|
|
"Run 'make audio.cpp' first.")
|
|
endif()
|
|
|
|
if(APPLE)
|
|
# Homebrew installs protobuf/grpc under a non-default prefix.
|
|
if(CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
|
|
set(HOMEBREW_DEFAULT_PREFIX "/opt/homebrew")
|
|
else()
|
|
set(HOMEBREW_DEFAULT_PREFIX "/usr/local")
|
|
endif()
|
|
link_directories("${HOMEBREW_DEFAULT_PREFIX}/lib")
|
|
include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
|
|
endif()
|
|
|
|
find_package(Threads REQUIRED)
|
|
find_package(Protobuf CONFIG QUIET)
|
|
if(NOT Protobuf_FOUND)
|
|
find_package(Protobuf REQUIRED)
|
|
endif()
|
|
find_package(gRPC CONFIG QUIET)
|
|
if(NOT gRPC_FOUND)
|
|
# Reached only on distros whose grpc++ packaging ships no CMake config.
|
|
# Ubuntu's libgrpc-dev does ship one, so this is dead code on LocalAI's own
|
|
# build distro. Kept for the distros that do not.
|
|
find_library(GRPCPP_LIB grpc++ REQUIRED)
|
|
find_library(GRPCPP_REFLECTION_LIB grpc++_reflection REQUIRED)
|
|
add_library(gRPC::grpc++ INTERFACE IMPORTED)
|
|
set_target_properties(gRPC::grpc++ PROPERTIES
|
|
INTERFACE_LINK_LIBRARIES "${GRPCPP_LIB}")
|
|
add_library(gRPC::grpc++_reflection INTERFACE IMPORTED)
|
|
set_target_properties(gRPC::grpc++_reflection PROPERTIES
|
|
INTERFACE_LINK_LIBRARIES "${GRPCPP_REFLECTION_LIB}")
|
|
endif()
|
|
|
|
find_program(_PROTOC NAMES protoc REQUIRED)
|
|
find_program(_GRPC_CPP_PLUGIN NAMES grpc_cpp_plugin REQUIRED)
|
|
|
|
get_filename_component(HW_PROTO "${CMAKE_CURRENT_SOURCE_DIR}/../../backend.proto" ABSOLUTE)
|
|
get_filename_component(HW_PROTO_PATH "${HW_PROTO}" PATH)
|
|
|
|
set(HW_PROTO_SRCS "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
|
|
set(HW_PROTO_HDRS "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
|
|
set(HW_GRPC_SRCS "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
|
|
set(HW_GRPC_HDRS "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
|
|
|
|
add_custom_command(
|
|
OUTPUT "${HW_PROTO_SRCS}" "${HW_PROTO_HDRS}" "${HW_GRPC_SRCS}" "${HW_GRPC_HDRS}"
|
|
COMMAND ${_PROTOC}
|
|
ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
--cpp_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
-I "${HW_PROTO_PATH}"
|
|
--plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN}"
|
|
"${HW_PROTO}"
|
|
DEPENDS "${HW_PROTO}")
|
|
|
|
add_library(hw_grpc_proto STATIC
|
|
${HW_GRPC_SRCS} ${HW_GRPC_HDRS}
|
|
${HW_PROTO_SRCS} ${HW_PROTO_HDRS})
|
|
target_include_directories(hw_grpc_proto PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
|
|
# Required on macOS: without these the Homebrew protobuf/grpc include dirs never
|
|
# reach this target and google/protobuf/runtime_version.h is not found.
|
|
target_link_libraries(hw_grpc_proto PUBLIC protobuf::libprotobuf gRPC::grpc++)
|
|
|
|
# Upstream's global add_compile_options(-Wall -Wextra -Wpedantic -pedantic-errors)
|
|
# is a directory property of the subdirectory and does not reach our targets.
|
|
#
|
|
# EXCLUDE_FROM_ALL is load-bearing, do not drop it: upstream's default target set
|
|
# includes its CLI, server, converter and test binaries, none of which we ship.
|
|
# Without it every build would compile all of them. The targets we do name in
|
|
# target_link_libraries below are still built on demand, so nothing is lost.
|
|
add_subdirectory("${AUDIO_CPP_DIR}" "${CMAKE_CURRENT_BINARY_DIR}/audio-cpp" EXCLUDE_FROM_ALL)
|
|
|
|
add_executable(${TARGET}
|
|
grpc-server.cpp
|
|
model_options.cpp
|
|
capability_routing.cpp
|
|
family_gate.cpp
|
|
loaded_model.cpp
|
|
audio_io.cpp
|
|
audio_units.cpp
|
|
transcript_assembly.cpp
|
|
result_map.cpp
|
|
inference_lane.cpp
|
|
)
|
|
|
|
# loaded_model.cpp mirrors engine::runtime::VoiceTaskKind onto its own Task enum.
|
|
# Its static_asserts catch an insertion or a reorder, but an enumerator APPENDED
|
|
# after the last one shifts no value, so no assertion can see it. What does see
|
|
# it is from_engine_task's switch over the engine enum, which carries no
|
|
# `default:` label. -Wswitch is only a warning by default, and a warning in a
|
|
# 600-file build log is a warning nobody reads, so promote it here: this is the
|
|
# difference between a build failure and a backend that silently runs the wrong
|
|
# task.
|
|
if(NOT MSVC)
|
|
set_source_files_properties(loaded_model.cpp PROPERTIES
|
|
COMPILE_OPTIONS "-Werror=switch")
|
|
endif()
|
|
|
|
target_include_directories(${TARGET} PRIVATE
|
|
"${AUDIO_CPP_DIR}/include"
|
|
"${CMAKE_CURRENT_SOURCE_DIR}")
|
|
|
|
target_link_libraries(${TARGET} PRIVATE
|
|
hw_grpc_proto
|
|
engine_runtime
|
|
ggml
|
|
gRPC::grpc++
|
|
gRPC::grpc++_reflection
|
|
protobuf::libprotobuf
|
|
Threads::Threads)
|
|
|
|
# ENGINE_ENABLE_CPU_ALL_VARIANTS builds ggml backends as shared objects that sit
|
|
# next to the binary in the package, so the binary must search its own directory.
|
|
# BUILD_WITH_INSTALL_RPATH keeps the build-tree binary at exactly "$ORIGIN".
|
|
# Upstream sets CMAKE_BUILD_WITH_INSTALL_RPATH in its own directory scope, which
|
|
# does not reach ours, so without this CMake also appends its build-tree library
|
|
# directory. That absolute build-host path would survive into the copied binary
|
|
# and let a package.sh that forgot to bundle libggml*.so still pass on the build
|
|
# machine while failing everywhere else.
|
|
set_target_properties(${TARGET} PROPERTIES
|
|
BUILD_RPATH "$ORIGIN"
|
|
INSTALL_RPATH "$ORIGIN"
|
|
BUILD_WITH_INSTALL_RPATH TRUE)
|
|
|
|
if(AUDIO_CPP_GRPC_BUILD_TESTS)
|
|
enable_testing()
|
|
|
|
# These are the units whose tests CANNOT run under
|
|
# backend/cpp/run-unit-tests.sh, because that script compiles each
|
|
# *_test.cpp standalone with no protobuf and no audio.cpp include path.
|
|
# They are named *_ctest.cpp so the script's glob does not pick them up and
|
|
# fail every backend's suite; everything that can be stdlib-only still is,
|
|
# and still lives in a *_test.cpp beside its unit.
|
|
#
|
|
# -Wall -Wextra -Wpedantic here and not on ${TARGET}: upstream's own
|
|
# add_compile_options is a property of its subdirectory and does not reach
|
|
# ours, so without naming them the tests would build as quietly as
|
|
# everything else.
|
|
add_executable(result_map_ctest
|
|
result_map_ctest.cpp
|
|
result_map.cpp
|
|
transcript_assembly.cpp
|
|
audio_units.cpp)
|
|
target_include_directories(result_map_ctest PRIVATE
|
|
"${AUDIO_CPP_DIR}/include"
|
|
"${CMAKE_CURRENT_SOURCE_DIR}"
|
|
# session.h reaches ggml.h through core/backend.h. Every other target
|
|
# here inherits that directory from the ggml target it links; this one
|
|
# links no ggml, so it has to name it.
|
|
"${AUDIO_CPP_DIR}/external/ggml/include")
|
|
# No engine_runtime: result_map touches only the plain structs in
|
|
# engine/framework/runtime/session.h, so the header is all it needs.
|
|
target_link_libraries(result_map_ctest PRIVATE
|
|
hw_grpc_proto
|
|
protobuf::libprotobuf
|
|
Threads::Threads)
|
|
target_compile_options(result_map_ctest PRIVATE -Wall -Wextra -Wpedantic)
|
|
add_test(NAME result_map COMMAND result_map_ctest)
|
|
|
|
add_executable(audio_io_ctest
|
|
audio_io_ctest.cpp
|
|
audio_io.cpp)
|
|
target_include_directories(audio_io_ctest PRIVATE
|
|
"${AUDIO_CPP_DIR}/include"
|
|
"${CMAKE_CURRENT_SOURCE_DIR}")
|
|
target_link_libraries(audio_io_ctest PRIVATE
|
|
engine_runtime
|
|
ggml
|
|
Threads::Threads)
|
|
target_compile_options(audio_io_ctest PRIVATE -Wall -Wextra -Wpedantic)
|
|
set_target_properties(audio_io_ctest PROPERTIES
|
|
BUILD_RPATH "$ORIGIN"
|
|
INSTALL_RPATH "$ORIGIN"
|
|
BUILD_WITH_INSTALL_RPATH TRUE)
|
|
add_test(NAME audio_io COMMAND audio_io_ctest)
|
|
endif()
|