https://github.com/megaease/easevoice-trainer
EaseVoice Trainer is a simple and user-friendly voice cloning and speech model trainer.
https://github.com/megaease/easevoice-trainer
speech-training text-to-speech tts voice-cloning
Last synced: 5 months ago
JSON representation
EaseVoice Trainer is a simple and user-friendly voice cloning and speech model trainer.
- Host: GitHub
- URL: https://github.com/megaease/easevoice-trainer
- Owner: megaease
- License: apache-2.0
- Created: 2025-01-07T13:49:22.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-04-18T05:29:56.000Z (6 months ago)
- Last Synced: 2025-04-18T18:36:51.664Z (6 months ago)
- Topics: speech-training, text-to-speech, tts, voice-cloning
- Language: Python
- Homepage:
- Size: 9.74 MB
- Stars: 167
- Watchers: 5
- Forks: 9
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# EaseVoice Trainer
[中文文档](./README.zh-CN.md) and [中文介绍视频](https://www.bilibili.com/video/BV1uaoDYVEbc/).
EaseVoice Trainer is a backend project designed to streamline and enhance the training process for voice synthesis and transformation. It is built upon the foundation of [GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS), inheriting its core concepts while introducing various improvements to make the system more accessible, elegant, and user-friendly.
Although EaseVoice Trainer takes inspiration from GPT-SoVITS, we chose not to directly fork the original repository due to significant design differences and unique objectives. Our focus is on creating a refined, modular system tailored to specific use cases and improving maintainability.
## Key Features
- User-Friendly Design: Simplified workflows and intuitive configurations make it easier for users to deploy and manage.
- Stability: ensuring consistent and reliable performance in the process of cloing and training.
- Training Observability: offering comprehensive monitoring tools, providing clear insights into progress of cloning and training with performance metrics.
- Clean Architecture: We have split the project into separate frontend and backend repositories for better modularity and maintainability. The portal repository is at [EaseVoice Trainer Frontend](https://github.com/megaease/easevoice-trainer-portal).
- RESTful API: The backend provides a RESTful API for easy integration with other services and applications.
- Scalability: Built with scalability in mind, making it suitable for both small-scale experiments and large-scale production.
- Integrate Tensorboard: We have integrated Tensorboard for real-time monitoring and visualization of training progress.
## Video introduction
[](https://www.youtube.com/watch?v=Rfv7hXFct00)
## Screenshorts
## Getting Started
### Pretrained Models
As in GPT-SoVITS, you can download [Pretrained Models](https://github.com/RVC-Boss/GPT-SoVITS#pretrained-models), and then put them into the `models` directory.
### Local Run
Before using EaseVoice Trainer, ensure you have the following installed:
• Python 3.9 or higher
• [uv](https://github.com/astral-sh/uv).
We leverage uv for robust and efficient project management. To start the server using uv:
```bash
uv sync
uv pip install whl/LangSegment-0.3.5-py3-none-any.whl
uv run src/main.py
```
### Run with Docker
1. Build the Docker image
```
cd scripts
docker build -t megaease/easevoice-trainer .
```
2. Run the Docker Container
```
docker run -p 8000:8000 megaease/easevoice-trainer
```
This command ensures that the application running inside the container on port 8000 is accessible locally via .
## Community
We welcome contributions from the community! Whether it’s fixing bugs, adding new features, or improving documentation, feel free to submit a pull request or open an issue.
## License
EaseVoice Trainer is under the Apache 2.0 license. See the [LICENSE](./LICENSE) file for details.