viXTTS is a text-to-speech voice generation tool that offers voice cloning voices in Vietnamese and other languages. This model is a fine-tuned version based on the XTTS-v2.0.3 model, utilizing the viVoice dataset. This repository is primarily intended for inference purposes.

The model can be accessed at: viXTTS on Hugging Face

For a quick demonstration, please refer to this notebook on Google Colab. Tutorial (Vietnamese): https://youtu.be/pbwEbpOy0m8?feature=shared

This code is specifically designed for running on Ubuntu or WSL2. It is not intended for use on macOS or Windows systems (might available later).

• At least 10GB of free disk space
• At least 16GB of RAM
• Nvidia GPU with a minimum of 4GB of VRAM
• By default, the model will utilize the GPU. In the absence of a GPU, it will run on the CPU and run much slower.

• Git
• Python version >=3.9 and <= 3.11. The default version is set to 3.11, but you can modify the Python version in the run.sh file.

git clone https://github.com/thinhlpg/vixtts-demo
cd vixtts-demo
./run.sh

1. Run run.sh (dependencies will be automatically installed for the first run).
2. Access the Gradio demo link.
3. Load the model and wait for it to load.
4. Inference and Enjoy 🤗
5. The result will be saved in output/

• Subpar performance for input sentences under 10 words in Vietnamese language (yielding inconsistent output and odd trailing sounds).
• This model is only fine-tuned in Vietnamese. The model's effectiveness with languages other than Vietnamese hasn't been tested, potentially reducing quality.

We would like to express our gratitude to all libraries, and resources that have played a role in the development of this demo, especially:

• Coqui TTS for XTTS foundation model and inference code
• Vinorm and Undethesea for Vietnamese text normalization
• Deepspeed for fast inference
• Huggingface Hub for hosting the model
• Gradio for web UI
• DeepFilterNet for noise removal

• You can message me directly on Facebook: https://fb.com/thinhlpg/ (preferred 🤗)
• GitHub: https://github.com/thinhlpg
• Email: [email protected] or [email protected]