Phase 15.5 구현: 화자 구분 (Speaker Diarization)

- Sidecar: pyannote /diarize 엔드포인트 + requirements.txt 업데이트
- LLM 기반 화자 추정 (Phase 1 — 오디오 보존 없이 전사 텍스트 분석)
- CaptionSegment에 speaker 필드 추가
- EditableSegment: 화자별 색상 바 + 화자 Chip 표시
- TranscriptTab: 화자 구분 버튼 + 진행률
- 설정: HuggingFace 토큰 입력 + Diarization 토글
- IPC: DIARIZE + DIARIZATION_PROGRESS 채널
- 에러코드: 895-897
- 12개 locale i18n

src/renderer/i18n/en.json

@@ -471,5 +471,13 @@
   "meeting.exportPdfFmt": "PDF (.pdf)",
   "meeting.polishFailed": "AI polishing failed",
   "meeting.viewDetailError": "Failed to load meeting details",
-  "meeting.startRecordingError": "Failed to start recording"
+  "meeting.startRecordingError": "Failed to start recording",
+  "meeting.diarize": "Diarize",
+  "meeting.diarizing": "Identifying speakers...",
+  "meeting.diarizeComplete": "Diarization complete",
+  "meeting.speaker": "Speaker",
+  "settings.hfToken": "HuggingFace Token",
+  "settings.hfTokenHint": "A HuggingFace token is required for speaker diarization",
+  "settings.diarization": "Speaker Diarization",
+  "settings.diarizationHint": "Automatically identify speakers after recording ends"
 }