tingshu

Tingshu (Tingshu)

Bringing the author's voice directly to you

Project Preview | Preview

Click to enter the project homepage｜Home

Quick Start | Quick Start

Click here to watch the video

1. Install Environment | Install Environment

./scripts/install.sh

2. Download Model Weights | Download Model Weights

./scripts/download_weights.sh

3. Start the Web UI | Run Web Interface

./scripts/run_gradio.sh

4. Generate Audio Data

./scripts/generate_web_data.sh

Project Optimization｜ TODO

• 1. The recordings generated using the new solution instead of the TTS method are problematic, have a pause, and have poor listening experience.
  Replace the TTS-generated recordings to address issues of lacking emotion, intonation, and poor listening experience.

• 2. Update web ui and replace static loading mode
  Update web ui and switch from static loading mode.

• 3. Add the content of the English version of autobiography data
  Add autobiographical content in the English version.

• 4. Appropriately increase background music content and sound effects
  Appropriately enhance background music and sound effects.

Disclaimer

This project is for study and research purposes only. Users must abide by local laws and regulations, including but not limited to DMCA related laws. We are not responsible for any illegal use.

This project is for research and learning purposes only. Users must comply with local laws and regulations, including but not limited to DMCA-related laws. We do not take any responsibility for illegal usage.

Technical acknowledgments | Credits

This project is built on the following open source projects:

• VITS2
• Bert-VITS2
• GPT VITS
• GPT-SoVITS
• Fish Speech