Styletts2 Lite

🚀 StyleTTS 2 - lite

A lightweight version of StyleTTS 2 for text-to-speech tasks

🚀 Quick Start

Explore the model on Hugging Face Spaces:
https://huggingface.co/spaces/dangtr0408/StyleTTS2-lite-space

For fine-tuning details, visit: https://github.com/dangtr0408/StyleTTS2-lite

✨ Features

• Initialized from the official StyleTTS 2 weights pre-trained on LibriTTS.
• Removed components like PLBert, Diffusion, Prosodic Encoder, SLM, and Spectral Normalization.
• Trained on the LibriTTS corpus for 100,000 steps.

📦 Installation

Prerequisites

• Python: Version 3.7 or higher
• Git: To clone the repository

Installation Steps

1. Clone the repository

git clone https://huggingface.co/dangtr0408/StyleTTS2-lite
cd StyleTTS2-lite

2. Install dependencies:

pip install -r requirements.txt

3. On Linux, manually install espeak:

sudo apt-get install espeak-ng

💻 Usage Examples

See run.ipynb file.

📚 Documentation

Training Details

1. Base Checkpoint: Initialized from the official StyleTTS 2 weights pre-trained on LibriTTS.
2. Components Removal: PLBert, Diffusion, Prosodic Encoder, SLM, and Spectral Normalization.
3. Training Data: LibriTTS corpus.
4. Training Schedule: Trained for 100,000 steps.

Model Architecture

📄 License

Code: MIT License

⚠️ Important Note

Before using these pre-trained models, you agree to inform the listeners that the speech samples are synthesized by the pre-trained models, unless you have the permission to use the voice you synthesize. That is, you agree to only use voices whose speakers grant the permission to have their voice cloned, either directly or by license before making synthesized voices public, or you have to publicly announce that these voices are synthesized if you do not have the permission to use these voices.

📖 References

• yl4579/StyleTTS2
• jik876/hifi-gan