feat: add FunASR speech recognition backend

backend/index.yaml

@@ -1002,6 +1002,31 @@
     nvidia-l4t-cuda-12: "nvidia-l4t-faster-qwen3-tts"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-faster-qwen3-tts"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
+- &funasr
+  urls:
+    - https://github.com/modelscope/FunASR
+  description: |
+    FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages.
+    Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese
+    accuracy), and built-in VAD, punctuation restoration, and speaker diarization.
+  tags:
+    - speech-recognition
+    - ASR
+    - multilingual
+  license: mit
+  name: "funasr"
+  alias: "funasr"
+  capabilities:
+    nvidia: "cuda12-funasr"
+    amd: "rocm-funasr"
+    metal: "metal-funasr"
+    default: "cpu-funasr"
+    nvidia-cuda-13: "cuda13-funasr"
+    nvidia-cuda-12: "cuda12-funasr"
+    nvidia-l4t: "nvidia-l4t-funasr"
+    nvidia-l4t-cuda-12: "nvidia-l4t-funasr"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-funasr"
+  icon: https://avatars.githubusercontent.com/u/109454077
 - &qwen-asr
   urls:
     - https://github.com/QwenLM/Qwen3-ASR
@@ -4586,3 +4611,86 @@
   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
+## funasr
+- !!merge <<: *funasr
+  name: "funasr-development"
+  capabilities:
+    nvidia: "cuda12-funasr-development"
+    amd: "rocm-funasr-development"
+    nvidia-l4t: "nvidia-l4t-funasr-development"
+    metal: "metal-funasr-development"
+    default: "cpu-funasr-development"
+    nvidia-cuda-13: "cuda13-funasr-development"
+    nvidia-cuda-12: "cuda12-funasr-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-funasr-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-funasr-development"
+- !!merge <<: *funasr
+  name: "cpu-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-funasr"
+  mirrors:
+    - localai/localai-backends:latest-cpu-funasr
+- !!merge <<: *funasr
+  name: "cpu-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-funasr"
+  mirrors:
+    - localai/localai-backends:master-cpu-funasr
+- !!merge <<: *funasr
+  name: "cuda12-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-funasr"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-funasr
+- !!merge <<: *funasr
+  name: "cuda12-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-funasr"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-funasr
+- !!merge <<: *funasr
+  name: "cuda13-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-funasr"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-funasr
+- !!merge <<: *funasr
+  name: "cuda13-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-funasr"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-funasr
+- !!merge <<: *funasr
+  name: "rocm-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-funasr"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-funasr
+- !!merge <<: *funasr
+  name: "rocm-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-funasr"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-funasr
+- !!merge <<: *funasr
+  name: "nvidia-l4t-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-funasr"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-funasr
+- !!merge <<: *funasr
+  name: "nvidia-l4t-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-funasr"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-funasr
+- !!merge <<: *funasr
+  name: "cuda13-nvidia-l4t-arm64-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-funasr"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-funasr
+- !!merge <<: *funasr
+  name: "cuda13-nvidia-l4t-arm64-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-funasr"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-funasr
+- !!merge <<: *funasr
+  name: "metal-funasr"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-funasr"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-funasr
+- !!merge <<: *funasr
+  name: "metal-funasr-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-funasr"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-funasr

backend/python/funasr/Makefile

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

backend/python/funasr/backend.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+"""
+gRPC backend for LocalAI wrapping FunASR (SenseVoice / Paraformer).
+"""
+from concurrent import futures
+import time
+import argparse
+import signal
+import sys
+import os
+import backend_pb2
+import backend_pb2_grpc
+import torch
+
+import grpc
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'common'))
+from grpc_auth import get_auth_interceptors
+
+
+_ONE_DAY_IN_SECONDS = 60 * 60 * 24
+MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
+
+
+class BackendServicer(backend_pb2_grpc.BackendServicer):
+    def Health(self, request, context):
+        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
+
+    def LoadModel(self, request, context):
+        from funasr import AutoModel
+
+        device = "cpu"
+        if request.CUDA and torch.cuda.is_available():
+            device = "cuda"
+        mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
+        if mps_available:
+            device = "mps"
+
+        model_id = request.Model or "iic/SenseVoiceSmall"
+
+        try:
+            print(f"Loading FunASR model: {model_id} on {device}", file=sys.stderr)
+            self.model = AutoModel(
+                model=model_id,
+                vad_model="fsmn-vad",
+                device=device,
+                disable_update=True,
+            )
+            print("FunASR model loaded successfully", file=sys.stderr)
+        except Exception as err:
+            print(f"[ERROR] LoadModel failed: {err}", file=sys.stderr)
+            import traceback
+            traceback.print_exc(file=sys.stderr)
+            return backend_pb2.Result(success=False, message=str(err))
+
+        return backend_pb2.Result(message="Model loaded successfully", success=True)
+
+    def AudioTranscription(self, request, context):
+        result_segments = []
+        text = ""
+        try:
+            audio_path = request.dst
+            if not audio_path or not os.path.exists(audio_path):
+                print(f"Error: Audio file not found: {audio_path}", file=sys.stderr)
+                return backend_pb2.TranscriptResult(segments=[], text="")
+
+            language = None
+            if request.language and request.language.strip():
+                language = request.language.strip()
+
+            kwargs = {}
+            if language:
+                kwargs["language"] = language
+
+            results = self.model.generate(input=audio_path, **kwargs)
+
+            if not results:
+                return backend_pb2.TranscriptResult(segments=[], text="")
+
+            for idx, r in enumerate(results):
+                seg_text = r.get("text", "") if isinstance(r, dict) else str(r)
+                text += seg_text
+                result_segments.append(backend_pb2.TranscriptSegment(
+                    id=idx,
+                    start=0,
+                    end=0,
+                    text=seg_text,
+                ))
+
+        except Exception as err:
+            print(f"Error in AudioTranscription: {err}", file=sys.stderr)
+            import traceback
+            traceback.print_exc(file=sys.stderr)
+            return backend_pb2.TranscriptResult(segments=[], text="")
+
+        return backend_pb2.TranscriptResult(segments=result_segments, text=text)
+
+
+def serve(address):
+    server = grpc.server(
+        futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),
+        ],
+        interceptors=get_auth_interceptors(),
+    )
+    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
+    server.add_insecure_port(address)
+    server.start()
+    print("Server started. Listening on: " + address, file=sys.stderr)
+
+    def signal_handler(sig, frame):
+        print("Received termination signal. Shutting down...")
+        server.stop(0)
+        sys.exit(0)
+
+    signal.signal(signal.SIGINT, signal_handler)
+    signal.signal(signal.SIGTERM, signal_handler)
+
+    try:
+        while True:
+            time.sleep(_ONE_DAY_IN_SECONDS)
+    except KeyboardInterrupt:
+        server.stop(0)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Run the gRPC server.")
+    parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
+    args = parser.parse_args()
+    serve(args.addr)

backend/python/funasr/install.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+
+EXTRA_PIP_INSTALL_FLAGS="--no-build-isolation"
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+if [ "x${BUILD_PROFILE}" == "xintel" ]; then
+    EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
+fi
+
+PYTHON_VERSION="3.12"
+PYTHON_PATCH="12"
+PY_STANDALONE_TAG="20251120"
+
+installRequirements

backend/python/funasr/requirements-cpu.txt

@@ -0,0 +1,3 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch
+funasr

backend/python/funasr/requirements-cublas12.txt

@@ -0,0 +1,3 @@
+--extra-index-url https://download.pytorch.org/whl/cu121
+torch
+funasr

backend/python/funasr/requirements-cublas13.txt

@@ -0,0 +1,3 @@
+--extra-index-url https://download.pytorch.org/whl/cu131
+torch
+funasr

backend/python/funasr/requirements-hipblas.txt

@@ -0,0 +1,3 @@
+--extra-index-url https://download.pytorch.org/whl/rocm6.1
+torch
+funasr

backend/python/funasr/requirements-intel.txt

@@ -0,0 +1,2 @@
+torch
+funasr

backend/python/funasr/requirements-l4t12.txt

@@ -0,0 +1 @@
+funasr

backend/python/funasr/requirements-l4t13.txt

@@ -0,0 +1 @@
+funasr

backend/python/funasr/requirements-mps.txt

@@ -0,0 +1,2 @@
+torch==2.7.1
+funasr

backend/python/funasr/requirements.txt

@@ -0,0 +1,5 @@
+grpcio==1.71.0
+protobuf
+certifi
+packaging==24.1
+setuptools

backend/python/funasr/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+startBackend $@

backend/python/funasr/test.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+ensureVenv
+
+python -m pytest -x -s test.py "$@"