apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-29 02:46:25 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

refactor: integrate local STT with existing upload flow

Browse source 
- Simplify STT_SERVICE config to local/MODEL_SIZE format
- Remove separate STT routes, integrate with document upload
- Add local STT support to audio file processing pipeline
- Remove React component, use existing upload interface
- Support both local Faster-Whisper and external STT services
- Tested with real speech: 99% accuracy, 2.87s processing
This commit is contained in:
Nabhan 2025-10-12 10:50:55 +05:00
parent bd6b198e20
commit cf0e265107
7 changed files with 47 additions and 238 deletions
Download patch file Download diff file Expand all files Collapse all files

6
surfsense_backend/.env.example
View file

@ -32,10 +32,8 @@ TTS_SERVICE_API_KEY=
TTS_SERVICE_API_BASE=
# STT Service Configuration
# Use 'local' for offline Faster-Whisper or LiteLLM provider
STT_SERVICE=local
# For local STT: Whisper model size (tiny, base, small, medium, large-v3)
LOCAL_STT_MODEL=base
# For local Faster-Whisper: local/MODEL_SIZE (tiny, base, small, medium, large-v3)
STT_SERVICE=local/base
# For LiteLLM STT Provider: https://docs.litellm.ai/docs/audio_transcription#supported-providers
# STT_SERVICE=openai/whisper-1
# STT_SERVICE_API_KEY=""