Folzo
8e683ca4fd
- Switched from large-v3 (1.56B) to distil-large-v3 (~756M) — 2x faster transcription - Increased CPU threads from 4 to 8 (Ryzen 5800X3D has 8c/16t) - French language quality preserved (~5% accuracy tradeoff for 2x speed) - Expected pipeline latency: 4-5s total (down from ~15s)
37 lines
843 B
YAML
37 lines
843 B
YAML
services:
|
|
effi-stt:
|
|
build: .
|
|
container_name: effi-stt
|
|
restart: unless-stopped
|
|
ports:
|
|
- "8200:8200"
|
|
environment:
|
|
- MODEL_SIZE=distil-large-v3
|
|
- DEVICE=cpu
|
|
- COMPUTE_TYPE=int8
|
|
- LANGUAGE=fr
|
|
- CPU_THREADS=8
|
|
- INACTIVITY_TIMEOUT=300
|
|
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
|