rishikanthc
|
3bbcbcfd63
|
fix: responsive design
|
2025-12-15 13:36:12 -08:00 |
|
rishikanthc
|
3a0f4fb9bc
|
feat: implement per-job SSE for real-time status updates
- Implement SSE Broadcaster with job-based subscription support
- Add /api/v1/events endpoint for SSE streaming
- Update transcription service and handlers to broadcast job events
- Implement frontend per-job SSE connection logic
- Remove legacy polling from audio list hooks
- Fix server shutdown deadlock issue
|
2025-12-14 19:09:52 -08:00 |
|
rishikanthc
|
f3266b31e5
|
feat: implement OpenAI transcription support
|
2025-12-01 14:00:33 -08:00 |
|
rishikanthc
|
99031c5054
|
major refactor
|
2025-11-26 19:45:31 -08:00 |
|
rishikanthc
|
acc4b3f458
|
fix pyannote diarization - separate pipelines depending on transcription model used
|
2025-11-25 19:11:34 -08:00 |
|
Geoff Tognetti
|
a9bfb9c771
|
Fix model storage location and Parakeet CUDA errors
This commit includes two related fixes:
1. Model Storage Location Fix:
- Models were stored outside persistent volume, causing re-downloads on every container rebuild
- Implemented dependency injection for adapter constructors
- Adapters now accept envPath parameter instead of hardcoded paths
- Added registerAdapters() function in main.go to register adapters after config loads
- Removed init() functions from all adapters (whisperx, parakeet, canary, sortformer, pyannote)
- Models now persist in /app/data/whisperx-env (inside Docker volume)
2. Parakeet CUDA Error 35 Fix:
- Fixed CUDA_ERROR_ILLEGAL_ADDRESS on long audio files (30+ minutes)
- Disabled CUDA graphs via change_decoding_strategy() in buffered inference
- Fixed buffered script check in PrepareEnvironment() to verify both transcribe.py and transcribe_buffered.py exist
- Verified working: 49min audio transcribed in 63sec (47x realtime)
Files Modified:
- cmd/server/main.go: Added registerAdapters() function
- internal/transcription/adapters/whisperx_adapter.go: Constructor accepts envPath, removed init()
- internal/transcription/adapters/parakeet_adapter.go: Constructor accepts envPath, removed init(), added CUDA fix and buffered script check
- internal/transcription/adapters/canary_adapter.go: Constructor accepts envPath, removed init()
- internal/transcription/adapters/sortformer_adapter.go: Constructor accepts envPath, removed init()
- internal/transcription/adapters/pyannote_adapter.go: Constructor accepts envPath, removed init()
|
2025-11-15 14:00:35 -08:00 |
|
rishikanthc
|
2b24e08055
|
improves logging
|
2025-09-11 10:32:36 -07:00 |
|
rishikanthc
|
81eb280da4
|
fixes pyannote diarization with the new unified arch
|
2025-09-10 21:25:37 -07:00 |
|
rishikanthc
|
978932e346
|
improve startup logs
|
2025-09-08 10:02:44 -07:00 |
|
rishikanthc
|
0bb41c41ec
|
optimizes backend for performance
|
2025-09-08 09:56:03 -07:00 |
|
rishikanthc
|
ce0b85fa23
|
adds support for video transcription - formatter run touched all files
|
2025-09-07 18:24:00 -07:00 |
|
rishikanthc
|
933a95f336
|
updates api doc path in backend
|
2025-08-30 09:23:07 -07:00 |
|
rishikanthc
|
21b0f47b5c
|
add github workflows
|
2025-08-28 15:13:35 -07:00 |
|
rishikanthc
|
03a07e5997
|
add docs for all api endpoints in swagger - remove default api keys
|
2025-08-28 08:53:33 -07:00 |
|
rishikanthc
|
f8659303c7
|
add initializing python environment
|
2025-08-27 08:56:58 -07:00 |
|
rishikanthc
|
52c3a19e99
|
quick transcription - without storing data api endpoints
|
2025-08-25 15:52:15 -07:00 |
|
rishikanthc
|
8e2cce27d0
|
implements user registratio on first step
|
2025-08-24 09:10:01 -07:00 |
|
rishikanthc
|
96aeaf1454
|
basic UI
|
2025-08-21 15:48:55 -07:00 |
|