metadata
datasets:
- LEMAS-Project/LEMAS-Dataset-train
- LEMAS-Project/LEMAS-Dataset-eval
language:
- it
- pt
- es
- fr
- de
- en
- zh
license: cc-by-nc-4.0
pipeline_tag: text-to-speech
tags:
- zero-shot
- multilingual
LEMAS-Edit
LEMAS-Edit is a multilingual zero-shot speech editing system, presented in the paper LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models.
- Project Page: https://lemas-project.github.io/LEMAS-Project
- Paper: https://arxiv.org/abs/2601.04233
- GitHub Repository: https://github.com/LEMAS-Project/LEMAS-Edit
- Hugging Face Demo: https://huggingface.co/spaces/LEMAS-Project/LEMAS-Edit
Supported Languages
The model supports 7 major languages for zero-shot synthesis:
- Chinese (zh)
- English (en)
- Spanish (es)
- French (fr)
- German (de)
- Italian (it)
- Portuguese (pt)
Training Data
LEMAS-Edit was trained on the subset of LEMAS-Dataset, 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.
Citation
@article{zhao2026lemas,
title={LEMAS: A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models},
author={Zhao, Zhiyuan and Lin, Lijian and Zhu, Ye and Xie, Kai and Liu, Yunfei and Li, Yu},
journal={arXiv preprint arXiv:2601.04233},
year={2026}
}