LEMAS-Project/LEMAS-TTS

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-TTS24 25LEMAS-TTS is a multilingual zero-shot text-to-speech 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-TTS)30- **Hugging Face Demo:** [https://huggingface.co/spaces/LEMAS-Project/LEMAS-TTS](https://huggingface.co/spaces/LEMAS-Project/LEMAS-TTS)31 32## Model Description33 34LEMAS-TTS is built upon a non-autoregressive flow-matching framework. It leverages the massive scale and linguistic diversity of the LEMAS-Dataset to achieve robust zero-shot multilingual synthesis. The model incorporates accent-adversarial training and CTC loss to mitigate cross-lingual accent issues, enhancing synthesis stability and quality across diverse languages.35 36## Supported Languages37 38The model supports 10 major languages for zero-shot synthesis:39- Chinese (zh)40- English (en)41- Spanish (es)42- Russian (ru)43- French (fr)44- German (de)45- Italian (it)46- Portuguese (pt)47- Indonesian (id)48- Vietnamese (vi)49 50## Training Data51 52LEMAS-TTS was trained on the [LEMAS-Dataset](https://huggingface.co/datasets/LEMAS-Project/LEMAS-Dataset-train), which is, to our knowledge, currently the largest open-source multilingual speech corpus with word-level timestamps. It covers over 150,000 hours across 10 major languages.53 54## Citation55 56```bibtex57@article{zhao2026lemas,58  title={LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models},59  author={Zhao, Zhiyuan and Lin, Lijian and Zhu, Ye and Xie, Kai and Liu, Yunfei and Li, Yu},60  journal={arXiv preprint arXiv:2601.04233},61  year={2026}62}63```