From 60facc72529abc0e746b6dd97ef0a6a0b6d83d75 Mon Sep 17 00:00:00 2001
From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com>
Date: Fri, 12 Jun 2026 22:32:42 +0200
Subject: [PATCH] fix(darwin): publish sherpa-onnx and speaker-recognition
 images for darwin/arm64 (#10275)

Neither the sherpa-onnx nor the speaker-recognition backend had a
darwin/arm64 image, so `local-ai backends install` failed with "no child
with platform darwin/arm64" on macOS. This left /v1/audio/diarization (the
sherpa-onnx path) and /v1/voice/embed without any usable backend on Apple
Silicon.

Both backends build on darwin/arm64:
- sherpa-onnx (Go) already fetches the onnxruntime osx-arm64 runtime in its
  Makefile; it only needed a darwin matrix entry (build-type metal, lang go,
  like whisper and silero-vad).
- speaker-recognition (Python) needed a requirements-mps.txt so the mps build
  installs plain onnxruntime (which ships a macOS arm64 wheel) instead of the
  onnxruntime-gpu pulled by its base requirements (which does not).

Add both to the includeDarwin build matrix, wire the metal capability and
metal image aliases into the gallery, and add the speaker-recognition
requirements-mps.txt.

Fixes #10268


Assisted-by: Claude:claude-opus-4-8 [Claude Code]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
---
 .github/backend-matrix.yml                    |  7 ++++++
 backend/index.yaml                            | 24 +++++++++++++++++++
 .../speaker-recognition/requirements-mps.txt  |  5 ++++
 3 files changed, 36 insertions(+)
 create mode 100644 backend/python/speaker-recognition/requirements-mps.txt

diff --git a/.github/backend-matrix.yml b/.github/backend-matrix.yml
index 1bb850de1..7df58bf6d 100644
--- a/.github/backend-matrix.yml
+++ b/.github/backend-matrix.yml
@@ -4461,6 +4461,10 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-silero-vad"
     build-type: "metal"
     lang: "go"
+  - backend: "sherpa-onnx"
+    tag-suffix: "-metal-darwin-arm64-sherpa-onnx"
+    build-type: "metal"
+    lang: "go"
   - backend: "local-store"
     tag-suffix: "-metal-darwin-arm64-local-store"
     build-type: "metal"
@@ -4468,3 +4472,6 @@ includeDarwin:
   - backend: "llama-cpp-quantization"
     tag-suffix: "-metal-darwin-arm64-llama-cpp-quantization"
     build-type: "mps"
+  - backend: "speaker-recognition"
+    tag-suffix: "-metal-darwin-arm64-speaker-recognition"
+    build-type: "mps"
diff --git a/backend/index.yaml b/backend/index.yaml
index b25d0a406..a3af8e01c 100644
--- a/backend/index.yaml
+++ b/backend/index.yaml
@@ -1254,6 +1254,7 @@
     default: "cpu-sherpa-onnx"
     nvidia: "cuda12-sherpa-onnx"
     nvidia-cuda-12: "cuda12-sherpa-onnx"
+    metal: "metal-sherpa-onnx"
 - !!merge <<: *neutts
   name: "neutts-development"
   capabilities:
@@ -4716,12 +4717,14 @@
     default: "cpu-speaker-recognition"
     nvidia: "cuda12-speaker-recognition"
     nvidia-cuda-12: "cuda12-speaker-recognition"
+    metal: "metal-speaker-recognition"
 - !!merge <<: *speakerrecognition
   name: "speaker-recognition-development"
   capabilities:
     default: "cpu-speaker-recognition-development"
     nvidia: "cuda12-speaker-recognition-development"
     nvidia-cuda-12: "cuda12-speaker-recognition-development"
+    metal: "metal-speaker-recognition-development"
 - !!merge <<: *speakerrecognition
   name: "cpu-speaker-recognition"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-speaker-recognition"
@@ -4742,6 +4745,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-speaker-recognition"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-speaker-recognition
+- !!merge <<: *speakerrecognition
+  name: "metal-speaker-recognition"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-speaker-recognition"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-speaker-recognition
+- !!merge <<: *speakerrecognition
+  name: "metal-speaker-recognition-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-speaker-recognition"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-speaker-recognition
 ## sherpa-onnx
 - !!merge <<: *sherpa-onnx
   name: "sherpa-onnx-development"
@@ -4749,6 +4762,7 @@
     default: "cpu-sherpa-onnx-development"
     nvidia: "cuda12-sherpa-onnx-development"
     nvidia-cuda-12: "cuda12-sherpa-onnx-development"
+    metal: "metal-sherpa-onnx-development"
 - !!merge <<: *sherpa-onnx
   name: "cpu-sherpa-onnx"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-sherpa-onnx"
@@ -4769,3 +4783,13 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-sherpa-onnx"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-12-sherpa-onnx
+- !!merge <<: *sherpa-onnx
+  name: "metal-sherpa-onnx"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-sherpa-onnx"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-sherpa-onnx
+- !!merge <<: *sherpa-onnx
+  name: "metal-sherpa-onnx-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-sherpa-onnx"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-sherpa-onnx
diff --git a/backend/python/speaker-recognition/requirements-mps.txt b/backend/python/speaker-recognition/requirements-mps.txt
new file mode 100644
index 000000000..9fe714abe
--- /dev/null
+++ b/backend/python/speaker-recognition/requirements-mps.txt
@@ -0,0 +1,5 @@
+torch
+torchaudio
+speechbrain
+transformers
+onnxruntime