feat(nemo): add Nemo (only asr for now) backend

.github/workflows/backend.yml

@@ -184,6 +184,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'cublas'
+            cuda-major-version: "12"
+            cuda-minor-version: "8"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-nemo'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "nemo"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -536,6 +549,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-nemo'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "nemo"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -1045,6 +1071,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'hipblas'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-rocm-hipblas-nemo'
+            runs-on: 'arc-runner-set'
+            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+            skip-drivers: 'false'
+            backend: "nemo"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1372,6 +1411,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: 'intel'
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-intel-nemo'
+            runs-on: 'arc-runner-set'
+            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+            skip-drivers: 'false'
+            backend: "nemo"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: 'intel'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1797,6 +1849,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-nemo'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'false'
+            backend: "nemo"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1886,6 +1951,9 @@ jobs:
           - backend: "qwen-asr"
             tag-suffix: "-metal-darwin-arm64-qwen-asr"
             build-type: "mps"
+          - backend: "nemo"
+            tag-suffix: "-metal-darwin-arm64-nemo"
+            build-type: "mps"
           - backend: "qwen-tts"
             tag-suffix: "-metal-darwin-arm64-qwen-tts"
             build-type: "mps"

.github/workflows/test-extra.yml

@@ -323,6 +323,25 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/qwen-asr
           make --jobs=5 --output-sync=target -C backend/python/qwen-asr test
+  tests-nemo:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential ffmpeg sox
+          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
+          # Install UV
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          pip install --user --no-cache-dir grpcio-tools==1.64.1
+      - name: Test nemo
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/nemo
+          make --jobs=5 --output-sync=target -C backend/python/nemo test
   tests-voxcpm:
     runs-on: ubuntu-latest
     steps:

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx backends/ace-step
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -318,6 +318,7 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/pocket-tts
 	$(MAKE) -C backend/python/qwen-tts
 	$(MAKE) -C backend/python/qwen-asr
+	$(MAKE) -C backend/python/nemo
 	$(MAKE) -C backend/python/voxcpm
 	$(MAKE) -C backend/python/whisperx
 	$(MAKE) -C backend/python/ace-step
@@ -334,6 +335,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/pocket-tts test
 	$(MAKE) -C backend/python/qwen-tts test
 	$(MAKE) -C backend/python/qwen-asr test
+	$(MAKE) -C backend/python/nemo test
 	$(MAKE) -C backend/python/voxcpm test
 	$(MAKE) -C backend/python/whisperx test
 	$(MAKE) -C backend/python/ace-step test
@@ -471,6 +473,7 @@ BACKEND_MOONSHINE = moonshine|python|.|false|true
 BACKEND_POCKET_TTS = pocket-tts|python|.|false|true
 BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
 BACKEND_QWEN_ASR = qwen-asr|python|.|false|true
+BACKEND_NEMO = nemo|python|.|false|true
 BACKEND_VOXCPM = voxcpm|python|.|false|true
 BACKEND_WHISPERX = whisperx|python|.|false|true
 BACKEND_ACE_STEP = ace-step|python|.|false|true
@@ -521,6 +524,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_MOONSHINE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_POCKET_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_ASR)))
+$(eval $(call generate-docker-build-target,$(BACKEND_NEMO)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
 $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
@@ -529,7 +533,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx docker-build-ace-step
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step
 
 ########################################################
 ### Mock Backend for E2E Tests

backend/index.yaml

@@ -103,7 +103,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr"
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
     metal: "metal-rfdetr"
     default: "cpu-rfdetr"
@@ -536,6 +536,27 @@
     nvidia-l4t-cuda-12: "nvidia-l4t-qwen-asr"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-asr"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
+- &nemo
+  urls:
+    - https://github.com/NVIDIA/NeMo
+  description: |
+    NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases.
+  tags:
+    - speech-recognition
+    - ASR
+    - NVIDIA
+  license: apache-2.0
+  name: "nemo"
+  alias: "nemo"
+  capabilities:
+    nvidia: "cuda12-nemo"
+    intel: "intel-nemo"
+    amd: "rocm-nemo"
+    metal: "metal-nemo"
+    default: "cpu-nemo"
+    nvidia-cuda-13: "cuda13-nemo"
+    nvidia-cuda-12: "cuda12-nemo"
+  icon: https://www.nvidia.com/favicon.ico
 - &voxcpm
   urls:
     - https://github.com/ModelBest/VoxCPM
@@ -1332,7 +1353,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr-development"
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
     metal: "metal-rfdetr-development"
     default: "cpu-rfdetr-development"
@@ -2337,6 +2358,77 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-asr"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-qwen-asr
+## nemo
+- !!merge <<: *nemo
+  name: "nemo-development"
+  capabilities:
+    nvidia: "cuda12-nemo-development"
+    intel: "intel-nemo-development"
+    amd: "rocm-nemo-development"
+    metal: "metal-nemo-development"
+    default: "cpu-nemo-development"
+    nvidia-cuda-13: "cuda13-nemo-development"
+    nvidia-cuda-12: "cuda12-nemo-development"
+- !!merge <<: *nemo
+  name: "cpu-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-nemo"
+  mirrors:
+    - localai/localai-backends:latest-cpu-nemo
+- !!merge <<: *nemo
+  name: "cpu-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-nemo"
+  mirrors:
+    - localai/localai-backends:master-cpu-nemo
+- !!merge <<: *nemo
+  name: "cuda12-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-nemo"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-nemo
+- !!merge <<: *nemo
+  name: "cuda12-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-nemo"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-nemo
+- !!merge <<: *nemo
+  name: "cuda13-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-nemo"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-nemo
+- !!merge <<: *nemo
+  name: "cuda13-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-nemo"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-nemo
+- !!merge <<: *nemo
+  name: "intel-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-nemo"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-nemo
+- !!merge <<: *nemo
+  name: "intel-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-nemo"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-nemo
+- !!merge <<: *nemo
+  name: "rocm-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-nemo"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-nemo
+- !!merge <<: *nemo
+  name: "rocm-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-nemo"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-nemo
+- !!merge <<: *nemo
+  name: "metal-nemo"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-nemo"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-nemo
+- !!merge <<: *nemo
+  name: "metal-nemo-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-nemo"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-nemo
 ## voxcpm
 - !!merge <<: *voxcpm
   name: "voxcpm-development"

backend/python/nemo/Makefile

@@ -0,0 +1,23 @@
+.PHONY: nemo-asr
+nemo-asr:
+	bash install.sh
+
+.PHONY: run
+run: nemo-asr
+	@echo "Running nemo-asr..."
+	bash run.sh
+	@echo "nemo-asr run."
+
+.PHONY: test
+test: nemo-asr
+	@echo "Testing nemo-asr..."
+	bash test.sh
+	@echo "nemo-asr tested."
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__