feat(silero): add Silero-vad backend (#4204)

* feat(vad): add silero-vad backend (WIP)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(vad): add API endpoint

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(vad): correctly place the onnxruntime libs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(vad): hook silero-vad to binary and container builds

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(gRPC): register VAD Server

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(Makefile): consume ONNX_OS consistently

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(Makefile): handle macOS

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

pkg/grpc/backend.go

@@ -53,4 +53,6 @@ type Backend interface {
 	Rerank(ctx context.Context, in *pb.RerankRequest, opts ...grpc.CallOption) (*pb.RerankResult, error)
 
 	GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opts ...grpc.CallOption) (*pb.MetricsResponse, error)
+
+	VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error)
 }

pkg/grpc/base/base.go

@@ -92,6 +92,10 @@ func (llm *Base) StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error)
 	return pb.StoresFindResult{}, fmt.Errorf("unimplemented")
 }
 
+func (llm *Base) VAD(*pb.VADRequest) (pb.VADResponse, error) {
+	return pb.VADResponse{}, fmt.Errorf("unimplemented")
+}
+
 func memoryUsage() *pb.MemoryUsageData {
 	mud := pb.MemoryUsageData{
 		Breakdown: make(map[string]uint64),

pkg/grpc/client.go

@@ -392,3 +392,21 @@ func (c *Client) GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opt
 	client := pb.NewBackendClient(conn)
 	return client.GetMetrics(ctx, in, opts...)
 }
+
+func (c *Client) VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error) {
+	if !c.parallel {
+		c.opMutex.Lock()
+		defer c.opMutex.Unlock()
+	}
+	c.setBusy(true)
+	defer c.setBusy(false)
+	c.wdMark()
+	defer c.wdUnMark()
+	conn, err := grpc.Dial(c.address, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return nil, err
+	}
+	defer conn.Close()
+	client := pb.NewBackendClient(conn)
+	return client.VAD(ctx, in, opts...)
+}

pkg/grpc/embed.go

@@ -87,6 +87,10 @@ func (e *embedBackend) Rerank(ctx context.Context, in *pb.RerankRequest, opts ..
 	return e.s.Rerank(ctx, in)
 }
 
+func (e *embedBackend) VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error) {
+	return e.s.VAD(ctx, in)
+}
+
 func (e *embedBackend) GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opts ...grpc.CallOption) (*pb.MetricsResponse, error) {
 	return e.s.GetMetrics(ctx, in)
 }

pkg/grpc/interface.go

@@ -24,6 +24,8 @@ type LLM interface {
 	StoresDelete(*pb.StoresDeleteOptions) error
 	StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error)
 	StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error)
+
+	VAD(*pb.VADRequest) (pb.VADResponse, error)
 }
 
 func newReply(s string) *pb.Reply {

pkg/grpc/server.go

@@ -227,6 +227,18 @@ func (s *server) StoresFind(ctx context.Context, in *pb.StoresFindOptions) (*pb.
 	return &res, nil
 }
 
+func (s *server) VAD(ctx context.Context, in *pb.VADRequest) (*pb.VADResponse, error) {
+	if s.llm.Locking() {
+		s.llm.Lock()
+		defer s.llm.Unlock()
+	}
+	res, err := s.llm.VAD(in)
+	if err != nil {
+		return nil, err
+	}
+	return &res, nil
+}
+
 func StartServer(address string, model LLM) error {
 	lis, err := net.Listen("tcp", address)
 	if err != nil {