marcel/familienarchiv
1
0
Fork 0
Code Issues 105 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

feat(training): add segmentation training pipeline and complete Part 6

Browse Source 
- Add /segtrain endpoint to OCR service (ZIP upload, ketos.segtrain,
  backup rotation, in-process model reload)
- Add segtrainModel() to OcrClient and RestClientOcrClient (10-min timeout,
  X-Training-Token header)
- Add SegmentationTrainingExportService: PAGE XML export with polygon
  de-normalization and per-page PNG rendering via PDFBox
- Add GET /api/ocr/segmentation-training-data/export endpoint
- Make TranscriptionBlock.text nullable for segmentation-only blocks
  (V31 migration)
- Add Paraglide i18n translation keys for all training UI strings (de/en/es)
- Pass source prop from TranscriptionEditView to TranscriptionBlock

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-13 15:15:17 +02:00
parent 86e9c05aaf
commit 9b2f91ee59
13 changed files with 383 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
frontend/messages/de.json
View File

@@ -533,5 +533,28 @@
"ocr_status_error": "OCR fehlgeschlagen",
"transcription_block_review": "Als geprüft markieren",
"transcription_block_unreview": "Markierung aufheben",
"transcription_reviewed_count": "{reviewed} von {total} geprüft"
"transcription_reviewed_count": "{reviewed} von {total} geprüft",
"training_ocr_heading": "Kurrent-Erkennung trainieren",
"training_ocr_description": "Starte ein neues Training mit den bisher geprüften OCR-Blöcken, um die Erkennungsgenauigkeit für Kurrentschrift zu verbessern.",
"training_ocr_blocks_ready": "{blocks} geprüfte Blöcke bereit / {docs} Dokumente",
"training_ocr_blocks_total": "(von {total} OCR-Blöcken gesamt)",
"training_start_btn": "Training starten",
"training_in_progress": "…",
"training_success": "Training wurde gestartet und abgeschlossen.",
"training_too_few_blocks": "Mindestens 5 geprüfte Blöcke erforderlich (aktuell: {available}).",
"training_service_down": "OCR-Dienst ist nicht erreichbar.",
"training_history_heading": "Verlauf",
"training_history_empty": "Noch keine Trainings-Läufe.",
"training_history_col_date": "Datum",
"training_history_col_status": "Status",
"training_history_col_blocks": "Blöcke",
"training_history_col_docs": "Dokumente",
"training_status_done": "Fertig",
"training_status_failed": "Fehler",
"training_status_running": "Läuft…",
"training_seg_heading": "Segmentierung trainieren",
"training_seg_description": "Starte ein neues Training mit annotierten Segmentierungsbereichen, um die Texterkennung zu verbessern.",
"training_seg_blocks_ready": "{blocks} Segmentierungsblöcke bereit",
"training_seg_too_few_blocks": "Mindestens 5 Segmentierungsblöcke erforderlich (aktuell: {available}).",
"transcription_block_segmentation_only": "Nur Segmentierung"
}