docs: update README with detailed desktop features and setup requirements

src/captions/processor.go

@@ -27,14 +27,27 @@ type Processor struct {
 	nextPreviewAt   int
 	previewReceived int
 	totalSamples    int
+	activity        Activity
+	speechKnown     bool
+	speechActive    bool
+}
+
+type Activity struct {
+	SpeechChanged      func(bool)
+	RecognitionChanged func(bool)
 }
 
 func New(settings config.Settings, transcriber Transcriber, emit func(Event) error) *Processor {
+	return NewWithActivity(settings, transcriber, emit, Activity{})
+}
+
+func NewWithActivity(settings config.Settings, transcriber Transcriber, emit func(Event) error, activity Activity) *Processor {
 	return &Processor{
 		settings:      settings,
 		transcriber:   transcriber,
 		emit:          emit,
 		nextPreviewAt: audio.DurationSamples(settings.ChunkDuration),
+		activity:      activity,
 	}
 }
 
@@ -43,6 +56,7 @@ func (p *Processor) Accept(samples []float32) error {
 		return nil
 	}
 	if p.settings.Mode == config.ModeFixed {
+		p.setSpeechActive(audio.RMSDBFS(samples) >= p.settings.PreviewThresholdDB)
 		return p.acceptFixed(samples)
 	}
 	return p.acceptVAD(samples)
@@ -84,6 +98,7 @@ func (p *Processor) acceptVAD(samples []float32) error {
 	p.transcriber.AcceptVAD(samples)
 
 	speechActive := p.transcriber.SpeechActive()
+	p.setSpeechActive(speechActive)
 	if speechActive && (p.previewActive || audio.RMSDBFS(samples) >= p.settings.PreviewThresholdDB) {
 		if !p.previewActive {
 			p.previewActive = true
@@ -144,7 +159,7 @@ func (p *Processor) resetPreview() {
 }
 
 func (p *Processor) emitProvisional() error {
-	text := strings.TrimSpace(p.transcriber.Decode(p.previewSamples))
+	text := strings.TrimSpace(p.decode(p.previewSamples))
 	if text == "" {
 		return nil
 	}
@@ -157,7 +172,7 @@ func (p *Processor) emitProvisional() error {
 }
 
 func (p *Processor) emitFinal(start, end int, samples []float32) error {
-	text := strings.TrimSpace(p.transcriber.Decode(samples))
+	text := strings.TrimSpace(p.decode(samples))
 	if text == "" {
 		return p.emit(Event{Kind: Hide})
 	}
@@ -169,6 +184,25 @@ func (p *Processor) emitFinal(start, end int, samples []float32) error {
 	})
 }
 
+func (p *Processor) decode(samples []float32) string {
+	if p.activity.RecognitionChanged != nil {
+		p.activity.RecognitionChanged(true)
+		defer p.activity.RecognitionChanged(false)
+	}
+	return p.transcriber.Decode(samples)
+}
+
+func (p *Processor) setSpeechActive(active bool) {
+	if p.speechKnown && p.speechActive == active {
+		return
+	}
+	p.speechKnown = true
+	p.speechActive = active
+	if p.activity.SpeechChanged != nil {
+		p.activity.SpeechChanged(active)
+	}
+}
+
 func (p *Processor) emitFixedFinal(start, end int, samples []float32) error {
 	if audio.RMSDBFS(samples) < p.settings.PreviewThresholdDB {
 		return p.emit(Event{Kind: Hide})