blob: 7cf401b71fa6e0ae1499139f731c9dc3dafbb5a7 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
|
services:
# Whisper.cpp STT service
whisper:
image: ghcr.io/ggml-org/whisper.cpp:main-cuda
container_name: whisper-stt
ports:
- "8081:8081"
volumes:
- whisper_models:/app/models
working_dir: /app
entrypoint: ""
command: >
sh -c "
if [ ! -f /app/models/ggml-large-v3-turbo.bin ]; then
echo 'Downloading ggml-large-v3-turbo model...'
./download-ggml-model.sh large-v3-turbo /app/models
fi &&
./build/bin/whisper-server -m /app/models/ggml-large-v3-turbo.bin -t 4 -p 1 --port 8081 --host 0.0.0.0
"
environment:
- WHISPER_LOG_LEVEL=3
# Restart policy in case the service fails
restart: unless-stopped
# Kokoro-FastAPI TTS service
kokoro-tts:
# image: ghcr.io/remsky/kokoro-fastapi-cpu:latest
image: ghcr.io/remsky/kokoro-fastapi-gpu:latest
container_name: kokoro-tts
ports:
- "8880:8880"
environment:
- API_LOG_LEVEL=INFO
# For GPU support, uncomment the following lines:
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: unless-stopped
volumes:
models:
driver: local
audio:
driver: local
whisper_models:
driver: local
|
