LEMAS-Project/LEMAS-Edit

1---2datasets:3- LEMAS-Project/LEMAS-Dataset-train4- LEMAS-Project/LEMAS-Dataset-eval5language:6- it7- pt8- es9- fr10- de11- vi12- id13- ru14- en15- zh16license: cc-by-4.017pipeline_tag: text-to-speech18tags:19- zero-shot20- multilingual21---22 23# LEMAS-Edit24 25LEMAS-Edit is a multilingual speech editing system, presented in the paper [LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models](https://huggingface.co/papers/2601.04233).26 27- **Project Page:** [https://lemas-project.github.io/LEMAS-Project](https://lemas-project.github.io/LEMAS-Project)28- **Paper:** [https://arxiv.org/abs/2601.04233](https://arxiv.org/abs/2601.04233)29- **GitHub Repository:** [https://github.com/LEMAS-Project/LEMAS-TTS](https://github.com/LEMAS-Project/LEMAS-Edit)30- **Hugging Face Demo:** [https://huggingface.co/spaces/LEMAS-Project/LEMAS-TTS](https://huggingface.co/spaces/LEMAS-Project/LEMAS-Edit)31 32 33## Supported Languages34 35The model supports 10 major languages for zero-shot synthesis:36- Chinese (zh)37- English (en)38- Spanish (es)39- Russian (ru)40- French (fr)41- German (de)42- Italian (it)43- Portuguese (pt)44- Indonesian (id)45- Vietnamese (vi)46 47## Citation48 49```bibtex50@article{zhao2026lemas,51  title={LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models},52  author={Zhao, Zhiyuan and Lin, Lijian and Zhu, Ye and Xie, Kai and Liu, Yunfei and Li, Yu},53  journal={arXiv preprint arXiv:2601.04233},54  year={2026}55}56```