feat: Create Effi-STT - custom STT solution for OpenWebUI
- FastAPI server with OpenAI-compatible API - Integration with faster-whisper (large-v3) - Full Docker support with docker-compose - Support for multiple languages (FR/EN/Auto) - Clean, maintainable codebase (~100 lines) - Health endpoint and error handling - Volume caching for models
This commit is contained in:
@@ -0,0 +1,35 @@
|
||||
services:
|
||||
effi-stt:
|
||||
build: .
|
||||
container_name: effi-stt
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "8200:8200"
|
||||
environment:
|
||||
- MODEL_SIZE=large-v3
|
||||
- DEVICE=cpu
|
||||
- COMPUTE_TYPE=int8
|
||||
- LANGUAGE=fr
|
||||
- CPU_THREADS=4
|
||||
volumes:
|
||||
# Cache pour les modèles (évite de re-télécharger)
|
||||
- effi-stt-cache:/root/.cache/huggingface
|
||||
# Pour GPU ROCm (optionnel, désactivé par défaut)
|
||||
# devices:
|
||||
# - /dev/kfd
|
||||
# - /dev/dri
|
||||
# group_add:
|
||||
# - "44"
|
||||
# - "991"
|
||||
# environment:
|
||||
# - HSA_OVERRIDE_GFX_VERSION=11.0.0
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://localhost:8200/health"]
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 3
|
||||
start_period: 60s
|
||||
|
||||
volumes:
|
||||
effi-stt-cache:
|
||||
driver: local
|
||||
Reference in New Issue
Block a user