Recording · Day 2

Council meeting - Public hearing

Technical details
Recording ID 935
Meeting ID 11
File path 5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv
All recordings
Recording information
Status
Completed
Duration
1h39m
Start time
2026-04-07 13:30
End time
2026-04-07 21:08
Extract audio
Extract WAV audio for transcription and diarization
Storage & files
File type Storage Path / Key Status Action
Video S3 5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv Exists
Transcript S3 f7b1272d-12b7-4322-a728-3837b008909d.json Exists
WAV S3 1a300f37-7a08-4b44-a7b6-8495c8212884.wav Exists
Diarization Pyannote S3 910af111-526b-4c6e-984f-e1b01d4dadcc.json Exists
Diarization Gemini S3 9b2a8798-3a89-46d9-b689-4da2083e6af0.json Exists
Diarization Consolidated S3 f2b0bb11-4412-4cfe-8078-4d5592795308.json Exists
Transcription progress
Completed
Loading transcription status…
Transcript & diarization
Full recording transcript and speaker diarization data available for download.
Gemini-refined · speaker labels improved with AI using meeting agenda context
Processing logs
91 entries 14 warnings
21:37:21 [INFO] Consolidation completed: 115 segments (reduced from 577)
21:37:21 [INFO] {"step": "consolidation", "status": "completed", "updated_at": "2026-09-07T15:37:21.103627-06:00", "consolidated_path": "9b2a8798-3a89-46d9-b689-4da2083e6af0.diarization.consolidated.json", "stats": {"original_segment_count": 577, "consolidated_segment_count": 115, "reduction_percent": 80.07}}
21:37:20 [INFO] {"step": "consolidation", "status": "processing", "updated_at": "2026-09-07T15:37:20.857785-06:00"}
21:37:20 [INFO] Speaker refinement completed
21:37:20 [INFO] {"step": "gemini", "status": "completed", "updated_at": "2026-09-07T15:37:20.847521-06:00", "output_path": "/tmp/tmputd4g1er.json"}
21:37:20 [INFO] ================================================================================
21:37:20 [INFO] CHUNKING COMPLETE: Successfully merged all 1 chunks in 54.7s
21:37:20 [INFO] ================================================================================
21:37:20 [INFO] ✓ Unique speaker mappings discovered: 14
21:37:20 [INFO] ✓ Speakers: 4 named, 17 generic
21:37:20 [INFO] ✓ Segment count: 577/577
21:37:20 [WARNING] Large gap detected at segment 555: 5687.725s -> 5696.585s
21:37:20 [WARNING] Large gap detected at segment 547: 5652.885s -> 5672.565s
21:37:20 [WARNING] Large gap detected at segment 490: 5278.985s -> 5284.985s
21:37:20 [WARNING] Large gap detected at segment 278: 3134.605s -> 3142.805s
21:37:20 [WARNING] Large gap detected at segment 257: 2858.865s -> 2869.065s
21:37:20 [WARNING] Large gap detected at segment 235: 2761.685s -> 2767.185s
21:37:20 [WARNING] Large gap detected at segment 234: 2752.345s -> 2758.225s
21:37:20 [WARNING] Large gap detected at segment 194: 2551.205s -> 2556.425s
21:37:20 [WARNING] Large gap detected at segment 157: 2376.325s -> 2382.085s
21:37:20 [WARNING] Large gap detected at segment 102: 1783.645s -> 1791.285s
21:37:20 [WARNING] Large gap detected at segment 85: 1525.965s -> 1538.505s
21:37:20 [WARNING] Large gap detected at segment 42: 1205.345s -> 1210.565s
21:37:20 [WARNING] Large gap detected at segment 39: 1191.325s -> 1198.585s
21:37:20 [INFO] VALIDATING MERGED RESULT
21:37:20 [INFO] --------------------------------------------------------------------------------
21:37:20 [DEBUG] Saved chunk 1 state to database
21:37:20 [INFO] Chunk 1: ✓ Refined successfully. Total speaker mappings: 14
21:37:20 [INFO] Chunk 1: Added 14 new speaker mappings. Total: 14
21:37:20 [INFO] Chunk 1: Gemini returned 21 speakers (4 refined: City Clerk City Clerk, Councillor A. Chabot, Councillor D. McLean, Public Speaker)
21:37:20 [INFO] Chunk 1: Successfully refined 92 segments with sparse mapping
21:37:20 [INFO] Saved parsed JSON: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.gemini_debug/chunk_001_parsed.json
21:37:20 [INFO] Saved chunk response: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.gemini_debug/chunk_001_response.txt
21:37:20 [INFO] Chunk 1: Gemini finish_reason: FinishReason.STOP
21:37:20 [INFO] Chunk 1: Received Gemini API response in 54.5s
21:36:26 [INFO] Chunk 1: Starting Gemini API call (model: gemini-2.5-pro, prompt length: 96382 chars)...
21:36:26 [INFO] Saved chunk input: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.gemini_debug/chunk_001_input.json
21:36:26 [INFO] Time range: 1094.6s - 5787.8s
21:36:26 [INFO] Processing chunk 1/1 (577 segments)
21:36:26 [INFO] --------------------------------------------------------------------------------
21:36:26 [INFO] Prior run found but no chunks completed. Starting from chunk 1/1
21:36:26 [INFO] Chunk tracking initialized in database
21:36:26 [INFO] Creating chunk tracking records for 1 chunks
21:36:26 [INFO] Split into 1 chunks
21:36:26 [INFO] ================================================================================
21:36:26 [INFO] City Clerk City Clerk, Councillor S. Sharp, Councillor J. Wyness, Councillor J. Mian, Councillor S. Chu, Councillor R. Dhaliwal, Councillor R. Pootmans, Councillor T. Wong, Councillor C. Walcott, Councillor G. Carra, Councillor A. Chabot, Councillor K. Penner, Councillor E. Spencer, Councillor D. McLean, Councillor P. Demong, Mayor J. Gondek, Council The provided text does not contain an attendance section or a list of council members., Administration There is no attendance information in the provided text., Public Speaker This document section does not contain any names of public speakers., Council no names can be extracted. The provided text does not contain an attendance section or a list of council members. Therefore, Administration There is no attendance section in the provided text., Administration An administration or staff attendance section was not found in the provided text.
21:36:26 [INFO] ================================================================================
21:36:26 [INFO] CHUNKING STRATEGY: Speaker list being used:
21:36:26 [INFO] ================================================================================
21:36:26 [INFO] CHUNKING: Processing 577 segments in chunks of 1500
21:36:26 [INFO] ================================================================================
21:36:26 [WARNING] Creating debug folder: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.gemini_debug. These folders are not auto-cleaned. Clean up with: rm -rf *.gemini_debug/
21:36:26 [INFO] Large meeting detected (577 segments). Using chunking strategy.
21:36:25 [INFO] Starting speaker refinement
21:36:25 [INFO] Cleanup completed: 18 segments corrected
21:36:25 [INFO] {"step": "cleanup", "status": "completed", "updated_at": "2026-09-07T15:36:25.228063-06:00", "applied_count": 18}
21:36:25 [INFO] {"step": "cleanup", "status": "processing", "updated_at": "2026-09-07T15:36:25.003609-06:00"}
21:36:24 [INFO] Starting name cleanup step
21:36:24 [INFO] Diarization completed and attached: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.diarization.pyannote.json
21:36:24 [INFO] Diarization completed successfully!
21:36:24 [INFO] {"step": "diarization", "status": "completed", "updated_at": "2026-09-07T15:36:24.983026-06:00", "output_path": "/tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.diarization.pyannote.json"}
21:36:24 [INFO] Extracted 577 turn-based segments
21:36:24 [INFO] Diarization results saved to /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.mkv.diarization.pyannote.json
21:36:24 [INFO] Job completed! Retrieving results...
21:36:24 [INFO] Job status: completed
21:36:24 [INFO] Speaker diarization completed
21:36:24 [INFO] Speaker diarization completed
21:36:24 [INFO] Poll #7: Status: succeeded
21:36:13 [INFO] Poll #6: Status: running
21:36:03 [INFO] Poll #5: Status: running
21:35:53 [INFO] Poll #4: Status: running
21:35:42 [INFO] Poll #3: Status: running
21:35:32 [INFO] Poll #2: Status: running
21:35:22 [INFO] Poll #1: Status: running
21:35:12 [INFO] Diarization job started (Job ID: b070728a-f902-4ce7-9c4a-aecf1697144d). Processing audio...
21:35:11 [INFO] Submitting diarization + transcription job to pyannote.ai (URL: https://ccai-prod.s3.amazonaws.com/1a300f37-7a08-4b44-a7b6-8495c8212884.wav?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAQK6LNXA7XP5KSEWG%2F20260907%2Fca-central-1%2Fs3%2Faws4_request&X-Amz-Date=20260907T213511Z&X-Amz-Expires=3600&X-Amz-SignedHeaders=host&X-Amz-Signature=b97b2572e152f03fd041bc3d3ed5ef6528d9683f15464bb034f5e7d0d0f582f1)
21:35:11 [INFO] Starting speaker diarization via pyannote.ai API
21:35:11 [INFO] Starting speaker diarization via pyannote.ai API
21:35:11 [INFO] Using S3 pre-signed URL for diarization
21:35:11 [INFO] {"step": "diarization", "status": "processing", "updated_at": "2026-09-07T15:35:11.439550-06:00"}
21:35:11 [INFO] Starting transcription + diarization
21:35:11 [INFO] Audio extracted and attached: /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.wav
21:35:11 [INFO] {"step": "extraction", "status": "completed", "updated_at": "2026-09-07T15:35:11.429313-06:00", "wav_path": "/tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.wav"}
21:35:09 [INFO] Audio extracted to /tmp/tmpvywtphbs/5c4a44b0-9c62-40cb-830a-dfd3a6a48be3.wav
21:34:51 [INFO] Extracting audio to WAV format
21:34:51 [INFO] Extracting audio to WAV format
21:34:51 [INFO] {"step": "extraction", "status": "processing", "updated_at": "2026-09-07T15:34:51.777207-06:00"}
21:34:51 [INFO] Starting audio extraction
21:34:47 [INFO] Downloading video from S3 for processing
20:01:51 [INFO] Download completed successfully
20:01:12 [INFO] Manual retry initiated by user