Implemented a module to detect backchannel segments, and updated the coalesce module to ignore them when coalescing same-speaker turns

internal/coalesce/coalesce.go

@@ -27,16 +27,24 @@ func Apply(in model.MergedTranscript, gap float64) (model.MergedTranscript, Summ
 	coalescedID := 0
 
 	current := newRun(in.Segments[0])
+	pendingBackchannels := make([]model.Segment, 0)
 	for _, segment := range in.Segments[1:] {
 		if current.canMerge(segment, gap) {
 			current.add(segment)
 			continue
 		}
+		if segment.Speaker != current.speaker() && hasCategory(segment, "backchannel") {
+			pendingBackchannels = append(pendingBackchannels, segment)
+			continue
+		}
 
 		coalescedID = appendRun(&out, current, coalescedID, &summary)
+		out.Segments = append(out.Segments, pendingBackchannels...)
+		pendingBackchannels = pendingBackchannels[:0]
 		current = newRun(segment)
 	}
-	appendRun(&out, current, coalescedID, &summary)
+	coalescedID = appendRun(&out, current, coalescedID, &summary)
+	out.Segments = append(out.Segments, pendingBackchannels...)
 
 	return out, summary
 }
@@ -56,6 +64,10 @@ func (r run) canMerge(next model.Segment, gap float64) bool {
 	return current.Speaker == next.Speaker && next.Start-current.End <= gap
 }
 
+func (r run) speaker() string {
+	return r.segments[0].Speaker
+}
+
 func (r *run) add(segment model.Segment) {
 	r.segments = append(r.segments, segment)
 }
@@ -116,3 +128,12 @@ func segmentRef(segment model.Segment) string {
 	}
 	return segment.Source
 }
+
+func hasCategory(segment model.Segment, category string) bool {
+	for _, existing := range segment.Categories {
+		if existing == category {
+			return true
+		}
+	}
+	return false
+}