🚀 Fish Speech 1.5 Ukrainian
This is a fine - tuned version of the Fish Speech 1.5 model, specifically designed for Ukrainian text - to - speech conversion, offering high - quality speech synthesis.
🚀 Quick Start
This README provides detailed information about the fine - tuned Fish Speech 1.5 model for the Ukrainian language.
✨ Features
- Fine - tuned for the Ukrainian language.
- Utilizes a private dataset with 240 hours of high - quality Ukrainian speech from 55 unique speakers.
- Follows the official Fish Speech fine - tuning guide for training.
📦 Installation
No installation steps are provided in the original document, so this section is skipped.
💻 Usage Examples
No code examples are provided in the original document, so this section is skipped.
📚 Documentation
Model Details
Property |
Details |
Base Model |
Fish Speech 1.5 |
Dataset Size |
240 hours |
Number of Speakers |
55 |
Training Steps |
100,000 |
Training Process |
Followed the official Fish Speech fine - tuning guide |
Training Dataset
The model was fine - tuned on a private dataset containing:
- 240 hours of Ukrainian speech
- 55 unique speakers
- High - quality studio recordings
- Various speech patterns and intonations
Fine - tuning Process
The fine - tuning process strictly followed the official Fish Speech documentation:
- Dataset preparation in the required format
- Batch extraction of semantic tokens using VQGAN
- Dataset packing into protobuf format
- LoRA fine - tuning of the LLAMA component
🔧 Technical Details
The fine - tuning process involves several key steps:
- First, the dataset is prepared in the required format to ensure compatibility with the model.
- Then, semantic tokens are batch - extracted using VQGAN, which helps in capturing the essential features of the speech.
- The dataset is then packed into the protobuf format for efficient storage and processing.
- Finally, LoRA fine - tuning of the LLAMA component is performed to adapt the model to the Ukrainian language.
📄 License
This model is released under the same license as the original Fish Speech model - [CC BY - NC - SA 4.0](https://creativecommons.org/licenses/by - nc - sa/4.0/).
This means you:
- Must give appropriate credit
- Cannot use the model for commercial purposes
- Must distribute any modifications under the same license
- Cannot apply legal terms that legally restrict others from doing anything the license permits
Acknowledgments
- Original Fish Speech model by Fish Audio
- Training infrastructure provided by [Fish Speech](https://github.com/fishaudio/fish - speech)