Recording · Day 1

Executive Committee

Technical details
Recording ID 948
Meeting ID 484
File path 15d37baa-7303-48d3-a3ea-cdf07b594399.mkv
Recording information
Status
Completed
Duration
2h18m
Start time
2026-04-14 13:30
End time
2026-04-14 21:48
Extract audio
Extract WAV audio for transcription and diarization
Storage & files
File type Storage Path / Key Status Action
Video S3 15d37baa-7303-48d3-a3ea-cdf07b594399.mkv Exists
Transcript S3 44556c11-f108-4387-b02e-838d3c1d39ea.json Exists
WAV S3 44740c83-0c80-466d-a725-e4f432d556a5.wav Exists
Diarization Pyannote S3 f3538330-9ba7-42f2-be63-1c3a74ef577a.json Exists
Diarization Gemini S3 f8b4fe45-5737-4aea-90ee-e34c4d0820e7.json Exists
Diarization Consolidated S3 d5c1393b-4da4-4f67-98db-bb8bfd5847fe.json Exists
Transcription progress
Completed
Loading transcription status…
Full recording transcript and speaker diarization data available for download.
Gemini-refined · speaker labels improved with AI using meeting agenda context
Processing logs
112 entries 23 warnings
20:41:50 [INFO] Consolidation completed: 433 segments (reduced from 984)
20:41:50 [INFO] {"step": "consolidation", "status": "completed", "updated_at": "2026-09-04T14:41:50.922809-06:00", "consolidated_path": "f8b4fe45-5737-4aea-90ee-e34c4d0820e7.diarization.consolidated.json", "stats": {"original_segment_count": 984, "consolidated_segment_count": 433, "reduction_percent": 56.0}}
20:41:50 [INFO] {"step": "consolidation", "status": "processing", "updated_at": "2026-09-04T14:41:50.652180-06:00"}
20:41:50 [INFO] Speaker refinement completed
20:41:50 [INFO] {"step": "gemini", "status": "completed", "updated_at": "2026-09-04T14:41:50.643801-06:00", "output_path": "/tmp/tmp8v529_kl.json"}
20:41:50 [INFO] ================================================================================
20:41:50 [INFO] CHUNKING COMPLETE: Successfully merged all 1 chunks in 101.3s
20:41:50 [INFO] ================================================================================
20:41:50 [INFO] ✓ Unique speaker mappings discovered: 18
20:41:50 [INFO] ✓ Speakers: 17 named, 10 generic
20:41:50 [INFO] ✓ Segment count: 984/984
20:41:50 [WARNING] Large gap detected at segment 977: 8240.365s -> 8246.305s
20:41:50 [WARNING] Large gap detected at segment 861: 7564.345s -> 7570.305s
20:41:50 [WARNING] Large gap detected at segment 837: 7408.045s -> 7414.305s
20:41:50 [WARNING] Large gap detected at segment 832: 7387.525s -> 7397.585s
20:41:50 [WARNING] Large gap detected at segment 460: 4423.305s -> 4434.565s
20:41:50 [WARNING] Large gap detected at segment 392: 3961.605s -> 3977.205s
20:41:50 [WARNING] Large gap detected at segment 389: 3947.845s -> 3953.625s
20:41:50 [WARNING] Large gap detected at segment 324: 3235.825s -> 3241.925s
20:41:50 [WARNING] Large gap detected at segment 322: 3214.445s -> 3223.745s
20:41:50 [WARNING] Large gap detected at segment 316: 3179.125s -> 3186.385s
20:41:50 [WARNING] Large gap detected at segment 264: 2709.005s -> 2720.645s
20:41:50 [WARNING] Large gap detected at segment 253: 2660.525s -> 2672.365s
20:41:50 [WARNING] Large gap detected at segment 239: 2589.005s -> 2595.865s
20:41:50 [WARNING] Large gap detected at segment 233: 2570.745s -> 2579.245s
20:41:50 [WARNING] Large gap detected at segment 192: 2325.345s -> 2338.045s
20:41:50 [WARNING] Large gap detected at segment 174: 2231.105s -> 2236.365s
20:41:50 [WARNING] Large gap detected at segment 171: 2218.485s -> 2228.645s
20:41:50 [WARNING] Large gap detected at segment 160: 2177.405s -> 2183.425s
20:41:50 [WARNING] Large gap detected at segment 138: 2088.325s -> 2099.065s
20:41:50 [WARNING] Large gap detected at segment 126: 1978.385s -> 1991.105s
20:41:50 [WARNING] Large gap detected at segment 82: 1652.525s -> 1679.485s
20:41:50 [WARNING] Large gap detected at segment 42: 1503.585s -> 1523.625s
20:41:50 [INFO] VALIDATING MERGED RESULT
20:41:50 [INFO] --------------------------------------------------------------------------------
20:41:50 [DEBUG] Saved chunk 1 state to database
20:41:50 [INFO] Chunk 1: ✓ Refined successfully. Total speaker mappings: 18
20:41:50 [INFO] Chunk 1: Added 18 new speaker mappings. Total: 18
20:41:50 [INFO] Chunk 1: Gemini returned 27 speakers (17 refined: Chief Financial Officer L. Tochor, City Clerk K. Martin, Councillor A. Chabot, Councillor D. McLean, Councillor D.J. Kelly, Councillor H. Clark, Councillor J. Wyness, Councillor K. Tyers, Councillor L. Johnston, Councillor M. Atkinson, Councillor M. Jamieson, Councillor N. Schmidt, Councillor R. Dhaliwal, Councillor-at-Large A. Yule, Councillor-at-Large J. Pantazopoulos, General Manager D. Morgan, Mayor J. Farkas)
20:41:50 [INFO] Chunk 1: Successfully refined 577 segments with sparse mapping
20:41:50 [INFO] Saved parsed JSON: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.gemini_debug/chunk_001_parsed.json
20:41:50 [INFO] Saved chunk response: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.gemini_debug/chunk_001_response.txt
20:41:50 [INFO] Chunk 1: Gemini finish_reason: FinishReason.STOP
20:41:50 [INFO] Chunk 1: Received Gemini API response in 100.9s
20:40:09 [INFO] Chunk 1: Starting Gemini API call (model: gemini-2.5-pro, prompt length: 147513 chars)...
20:40:09 [INFO] Saved chunk input: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.gemini_debug/chunk_001_input.json
20:40:09 [INFO] Time range: 1285.8s - 8268.7s
20:40:09 [INFO] Processing chunk 1/1 (984 segments)
20:40:09 [INFO] --------------------------------------------------------------------------------
20:40:09 [INFO] Prior run found but no chunks completed. Starting from chunk 1/1
20:40:09 [INFO] Chunk tracking initialized in database
20:40:09 [INFO] Creating chunk tracking records for 1 chunks
20:40:09 [INFO] Split into 1 chunks
20:40:09 [INFO] ================================================================================
20:40:09 [INFO] Mayor J. Farkas, Councillor D.J. Kelly, Councillor A. Chabot, Councillor R. Dhaliwal, Councillor-at-Large J. Pantazopoulos, Councillor J. Wyness, Councillor-at-Large A. Yule, Councillor M. Atkinson, Councillor H. Clark, Councillor M. Jamieson, Councillor L. Johnston, Councillor D. McLean, Councillor N. Schmidt, Councillor K. Tyers, Councillor R. Ward, Chief Administrative Officer D. Duckworth, Chief Operating Officer S. Dalgleish, City Solicitor and General Counsel J. Floen, Chief Financial Officer L. Tochor, A/General Manager J. Kapala, General Manager K. Black, General Manager D. Hamilton, General Manager D. Morgan, General Manager M. Thompson, City Clerk K. Martin, Senior Legislative Specialist K. Picketts, Public Speaker There were no public speakers listed in the provided meeting minutes.
20:40:09 [INFO] ================================================================================
20:40:09 [INFO] CHUNKING STRATEGY: Speaker list being used:
20:40:09 [INFO] ================================================================================
20:40:09 [INFO] CHUNKING: Processing 984 segments in chunks of 1500
20:40:09 [INFO] ================================================================================
20:40:09 [WARNING] Creating debug folder: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.gemini_debug. These folders are not auto-cleaned. Clean up with: rm -rf *.gemini_debug/
20:40:09 [INFO] Large meeting detected (984 segments). Using chunking strategy.
20:40:02 [INFO] Starting speaker refinement
20:40:01 [INFO] Cleanup completed: 80 segments corrected
20:40:01 [INFO] {"step": "cleanup", "status": "completed", "updated_at": "2026-09-04T14:40:01.460913-06:00", "applied_count": 80}
20:40:01 [INFO] {"step": "cleanup", "status": "processing", "updated_at": "2026-09-04T14:40:01.113226-06:00"}
20:40:01 [INFO] Starting name cleanup step
20:40:01 [INFO] Diarization completed and attached: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.diarization.pyannote.json
20:40:01 [INFO] Diarization completed successfully!
20:40:01 [INFO] {"step": "diarization", "status": "completed", "updated_at": "2026-09-04T14:40:01.077900-06:00", "output_path": "/tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.diarization.pyannote.json"}
20:40:00 [INFO] Extracted 984 turn-based segments
20:40:00 [INFO] Diarization results saved to /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.mkv.diarization.pyannote.json
20:40:00 [INFO] Job completed! Retrieving results...
20:40:00 [INFO] Job status: completed
20:40:00 [INFO] Speaker diarization completed
20:40:00 [INFO] Speaker diarization completed
20:40:00 [INFO] Poll #17: Status: succeeded
20:39:49 [INFO] Poll #16: Status: running
20:39:39 [INFO] Poll #15: Status: running
20:39:28 [INFO] Poll #14: Status: running
20:39:18 [INFO] Poll #13: Status: running
20:39:08 [INFO] Poll #12: Status: running
20:38:57 [INFO] Poll #11: Status: running
20:38:47 [INFO] Poll #10: Status: running
20:38:37 [INFO] Poll #9: Status: running
20:38:26 [INFO] Poll #8: Status: running
20:38:16 [INFO] Poll #7: Status: running
20:38:05 [INFO] Poll #6: Status: running
20:37:55 [INFO] Poll #5: Status: running
20:37:45 [INFO] Poll #4: Status: running
20:37:35 [INFO] Poll #3: Status: running
20:37:24 [INFO] Poll #2: Status: running
20:37:14 [INFO] Poll #1: Status: running
20:37:04 [INFO] Diarization job started (Job ID: 1326381a-8d5c-4098-b7ec-7b7a69db8476). Processing audio...
20:37:03 [INFO] Submitting diarization + transcription job to pyannote.ai (URL: https://ccai-prod.s3.amazonaws.com/44740c83-0c80-466d-a725-e4f432d556a5.wav?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAQK6LNXA7XP5KSEWG%2F20260904%2Fca-central-1%2Fs3%2Faws4_request&X-Amz-Date=20260904T203703Z&X-Amz-Expires=3600&X-Amz-SignedHeaders=host&X-Amz-Signature=3ceaa22d5afc72c66ae92d7b9b3ab66701b7f5cc8f2846f9d24e9908560f3a92)
20:37:03 [INFO] Starting speaker diarization via pyannote.ai API
20:37:03 [INFO] Starting speaker diarization via pyannote.ai API
20:37:03 [INFO] Using S3 pre-signed URL for diarization
20:37:03 [INFO] {"step": "diarization", "status": "processing", "updated_at": "2026-09-04T14:37:03.592952-06:00"}
20:37:03 [INFO] Starting transcription + diarization
20:37:03 [INFO] Audio extracted and attached: /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.wav
20:37:03 [INFO] {"step": "extraction", "status": "completed", "updated_at": "2026-09-04T14:37:03.575468-06:00", "wav_path": "/tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.wav"}
20:37:01 [INFO] Audio extracted to /tmp/tmpff7ml3o2/15d37baa-7303-48d3-a3ea-cdf07b594399.wav
20:36:35 [INFO] Extracting audio to WAV format
20:36:35 [INFO] Extracting audio to WAV format
20:36:35 [INFO] {"step": "extraction", "status": "processing", "updated_at": "2026-09-04T14:36:35.378818-06:00"}
20:36:35 [INFO] Starting audio extraction
20:36:29 [INFO] Downloading video from S3 for processing
14:29:49 [INFO] Recording 948 complete
14:28:35 [INFO] Resolved eSCRIBE URL: https://pub-calgary.escribemeetings.com/Players/ISIStandAlonePlayer.aspx?Id=f8fcafe9-29d8-4ac0-be0b-bdb8c4f0712d
14:28:35 [INFO] Starting backfill for meeting 484 part 1
01:00:17 [INFO] Already COMPLETED; early-exit (part 1)