This Docker image is designed to facilitate the deployment and execution of the Retrieval-based Voice Conversion WebUI project. It includes all the necessary dependencies, pre-trained models, and services, including TensorBoard for monitoring.
Additionally, FileBrowser is integrated into this image to provide a file management interface, making it easier to manage datasets and files within the container.
# docker-compose.yml
version: '3'
services:
rvc-aio:
build: .
runtime: nvidia
environment:
- NVIDIA_VISIBLE_DEVICES=1
ports:
- 17865:7865
- 16006:6006
- 18080:8080
volumes:
- ./weights:/app/assets/weights
- ./logs:/app/logs
- ./audio:/app/audio
- ./dataset:/app/dataset
For additional information and details on the Retrieval-based Voice Conversion project, refer to the official GitHub repository.
You can build this image yourself, for that, go check the GitHub's project: GitHub repository
Content type
Image
Digest
sha256:1b6211acc…
Size
7.2 GB
Last updated
almost 3 years ago
docker pull kamilake/rvc