From 434fd5b31ca0fc9d510bed9a7d7a5554c6823743 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Fri, 12 Jun 2026 17:40:17 +0000
Subject: [PATCH] fix(darwin): publish sherpa-onnx and speaker-recognition
 images for darwin/arm64

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

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
---
 .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 1bb850de1233..7df58bf6d1d6 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 b25d0a406261..a3af8e01cc95 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 000000000000..9fe714abee09
--- /dev/null
+++ b/backend/python/speaker-recognition/requirements-mps.txt
@@ -0,0 +1,5 @@
+torch
+torchaudio
+speechbrain
+transformers
+onnxruntime