Phase 3: Speaker diarization and full transcription pipeline

- Implement DiarizeService with pyannote.audio speaker detection
- Build PipelineService combining transcribe → diarize → merge with
  overlap-based speaker assignment per segment
- Add pipeline.start and diarize.start IPC handlers
- Add run_pipeline Tauri command for full pipeline execution
- Wire frontend to use pipeline: speakers auto-created with colors,
  segments assigned to detected speakers
- Build SpeakerManager with rename support (double-click or edit button)
- Add speaker color coding throughout transcript display
- Add pyannote.audio dependency
- Tests: 24 Python (including merge logic), 6 Rust, 0 Svelte errors

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/routes/+page.svelte

@@ -7,7 +7,7 @@
   import AIChatPanel from '$lib/components/AIChatPanel.svelte';
   import ProgressOverlay from '$lib/components/ProgressOverlay.svelte';
   import { segments, speakers } from '$lib/stores/transcript';
-  import type { Segment, Word } from '$lib/types/transcript';
+  import type { Segment, Speaker } from '$lib/types/transcript';
 
   let waveformPlayer: WaveformPlayer;
   let audioUrl = $state('');
@@ -16,6 +16,9 @@
   let transcriptionStage = $state('');
   let transcriptionMessage = $state('');
 
+  // Speaker color palette for auto-assignment
+  const speakerColors = ['#e94560', '#4ecdc4', '#ffe66d', '#a8e6cf', '#ff8b94', '#c7ceea', '#ffd93d', '#6bcb77'];
+
   function handleWordClick(timeMs: number) {
     waveformPlayer?.seekTo(timeMs);
   }
@@ -32,11 +35,10 @@
     if (!filePath) return;
 
     // Convert file path to URL for wavesurfer
-    // In Tauri, we can use convertFileSrc or asset protocol
     audioUrl = `asset://localhost/${encodeURIComponent(filePath)}`;
     waveformPlayer?.loadAudio(audioUrl);
 
-    // Start transcription
+    // Start pipeline (transcription + diarization)
     isTranscribing = true;
     transcriptionProgress = 0;
     transcriptionStage = 'Starting...';
@@ -47,6 +49,7 @@
           text: string;
           start_ms: number;
           end_ms: number;
+          speaker: string | null;
           words: Array<{
             word: string;
             start_ms: number;
@@ -56,14 +59,29 @@
         }>;
         language: string;
         duration_ms: number;
-      }>('transcribe_file', { filePath });
+        speakers: string[];
+        num_speakers: number;
+      }>('run_pipeline', { filePath });
+
+      // Create speaker entries from pipeline result
+      const newSpeakers: Speaker[] = (result.speakers || []).map((label, idx) => ({
+        id: `speaker-${idx}`,
+        project_id: '',
+        label,
+        display_name: null,
+        color: speakerColors[idx % speakerColors.length],
+      }));
+      speakers.set(newSpeakers);
+
+      // Build speaker label → id lookup
+      const speakerLookup = new Map(newSpeakers.map(s => [s.label, s.id]));
 
       // Convert result to our store format
       const newSegments: Segment[] = result.segments.map((seg, idx) => ({
         id: `seg-${idx}`,
         project_id: '',
         media_file_id: '',
-        speaker_id: null,
+        speaker_id: seg.speaker ? (speakerLookup.get(seg.speaker) ?? null) : null,
         start_ms: seg.start_ms,
         end_ms: seg.end_ms,
         text: seg.text,
@@ -85,8 +103,8 @@
 
       segments.set(newSegments);
     } catch (err) {
-      console.error('Transcription failed:', err);
-      alert(`Transcription failed: ${err}`);
+      console.error('Pipeline failed:', err);
+      alert(`Pipeline failed: ${err}`);
     } finally {
       isTranscribing = false;
     }