Brummel
6e6cfd77b7
Off-the-shelf Whisper wrappers hardcode faster-whisper defaults that cause cascading hallucinations on real dictations (2/13 runs against ahmetoner v1.9.1). This thin FastAPI service mirrors the /asr interface but fixes condition_on_previous_text=False, temperature=0.0, and vad_filter=True so the Axum server can switch by changing WHISPER_URL.
22 lines
555 B
YAML
22 lines
555 B
YAML
services:
|
|
doctate-whisper:
|
|
image: doctate-whisper:latest
|
|
container_name: doctate-whisper
|
|
environment:
|
|
- WHISPER_MODEL=large-v3-turbo
|
|
- WHISPER_COMPUTE_TYPE=float16
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
volumes:
|
|
- /opt/stacks/doctate-whisper/models:/models
|
|
ports:
|
|
- "9001:9001"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|