feat(voice-detect): wire backend into index, gallery and build

Register the voice-detect.cpp speaker-recognition + voice-analysis
backend (added in Voice-INT-A) into LocalAI's distribution surfaces,
mirroring the ced backend (the closest mudler C++/ggml audio analogue):

- backend/index.yaml: add the &voicedetect meta-backend (capabilities
  platform map, no top-level uri) plus the full set of concrete per-arch
  image entries (cpu/cuda12/cuda13/metal/rocm/sycl/vulkan/l4t and the
  -development variants). Referential integrity audited - every alias
  target resolves.
- gallery/index.yaml: add 5 model entries on backend voice-detect -
  ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++ and the
  wav2vec2 age/gender/emotion analyze model. The engine architecture is
  read from GGUF metadata (voicedetect.arch) at load. GGUF artifacts are
  not yet published: each files: entry points at the intended
  mudler/voice-detect-gguf location with a TODO to fill sha256 after
  upload (no fabricated hashes).
- .github/backend-matrix.yml: add the linux build matrix block + the
  darwin metal entry mirroring ced.
- .github/workflows/bump_deps.yaml: track mudler/voice-detect.cpp via
  VOICEDETECT_VERSION (pin 47546430, = 4754643).
- core/config/backend_capabilities.go: register voice-detect in the
  backend capability map (VoiceVerify/VoiceEmbed/VoiceAnalyze ->
  speaker_recognition), mirroring speaker-recognition.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
This commit is contained in:
Ettore Di Giacinto
2026-06-22 00:15:00 +00:00
parent 01e098a844
commit 2c5ed413cb
5 changed files with 490 additions and 0 deletions

View File

@@ -3723,6 +3723,154 @@ include:
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# voice-detect
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-voice-detect'
base-image: "ubuntu:24.04"
ubuntu-version: '2404'
runs-on: 'ubuntu-24.04-arm'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
platform-tag: 'amd64'
tag-latest: 'auto'
tag-suffix: '-cpu-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/arm64'
platform-tag: 'arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-voice-detect'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
platform-tag: 'amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-voice-detect'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/arm64'
platform-tag: 'arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-voice-detect'
runs-on: 'ubuntu-24.04-arm'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-voice-detect'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2204'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-voice-detect'
base-image: "rocm/dev-ubuntu-24.04:7.2.1"
runs-on: 'ubuntu-latest'
skip-drivers: 'false'
backend: "voice-detect"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# acestep-cpp
- build-type: ''
cuda-major-version: ""
@@ -4906,6 +5054,10 @@ includeDarwin:
tag-suffix: "-metal-darwin-arm64-ced"
build-type: "metal"
lang: "go"
- backend: "voice-detect"
tag-suffix: "-metal-darwin-arm64-voice-detect"
build-type: "metal"
lang: "go"
- backend: "acestep-cpp"
tag-suffix: "-metal-darwin-arm64-acestep-cpp"
build-type: "metal"

View File

@@ -46,6 +46,10 @@ jobs:
variable: "CED_VERSION"
branch: "master"
file: "backend/go/ced/Makefile"
- repository: "mudler/voice-detect.cpp"
variable: "VOICEDETECT_VERSION"
branch: "master"
file: "backend/go/voice-detect/Makefile"
- repository: "mudler/depth-anything.cpp"
variable: "DEPTHANYTHING_VERSION"
branch: "master"