Pin the keyword models to one thread each and ship them (V-487)

The gate loaded and worked on workpc and took mavwaked from 68% of one core
to 335%. onnxruntime sizes its intra-op pool to every core and spins between
runs, which an always-on gate scoring three graphs twelve times a second
provokes for the whole day. One thread per session brings it to 81%, so the
keyword costs about 13% of a core, and each graph still finishes well inside
its 80ms.

The unit now passes the three -wake- flags and the models sit beside
silero_vad.onnx in ~/.local/share/maven/models. The threshold is left at the
binary's default so there is one place to change it.

cmd/mavwaked/wakefeatures.go

@@ -71,15 +71,30 @@ func newWakeModels(melPath, embedPath, headPath, libPath string) (*wakeModels, e
 			return nil, fmt.Errorf("wake word: onnx runtime: %w", err)
 		}
 	}
+	// One thread per session, not the default of every core. Measured on
+	// workpc: the default took mavwaked from 68% of one core to 335% of
+	// three, for three graphs that each run in well under 80ms single
+	// threaded. An always-on gate that eats a quarter of the workstation is
+	// not a gate he will leave running.
+	opts, err := ort.NewSessionOptions()
+	if err != nil {
+		return nil, fmt.Errorf("wake word: session options: %w", err)
+	}
+	defer opts.Destroy()
+	if err := opts.SetIntraOpNumThreads(1); err != nil {
+		return nil, fmt.Errorf("wake word: intra-op threads: %w", err)
+	}
+	if err := opts.SetInterOpNumThreads(1); err != nil {
+		return nil, fmt.Errorf("wake word: inter-op threads: %w", err)
+	}
 	open := func(p string, in, out []string) (*ort.DynamicAdvancedSession, error) {
-		s, err := ort.NewDynamicAdvancedSession(p, in, out, nil)
+		s, err := ort.NewDynamicAdvancedSession(p, in, out, opts)
 		if err != nil {
 			return nil, fmt.Errorf("wake word: load %s: %w", p, err)
 		}
 		return s, nil
 	}
 	m := &wakeModels{}
-	var err error
 	if m.mel, err = open(melPath, []string{"input"}, []string{"output"}); err != nil {
 		return nil, err
 	}