---

📋 Overview

LLM-SRT is a speech translation toolkit built upon SLAM-LLM, featuring a series of models for scalable many-to-many speech-to-text translation.

📰 News

• 2026-04-15: MCAT paper published in IEEE TASLP.
• 2026-01-26: SMT paper accepted by ICLR 2026.
• 2026-01-15: SLAM-LLM paper accepted by IEEE JSTSP.
• 2025-05-16: LLM-SRT paper accepted by ACL 2025.

🚀 Models

🔧 Installation

# Install uv (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the repository
git clone https://github.com/yxduir/LLM-SRT
cd LLM-SRT

# Create and activate virtual environment
uv venv --python 3.10
source .venv/bin/activate

# Install dependencies
cd SLAM-LLM
uv pip install -r requirements.txt
uv pip install -e .
cd ..

📖 Citation

If you find this project helpful for your research, please consider citing the relevant papers:

@misc{du2026bandwidthefficientprivacypreservingedgecloudmanytomany,
      title={Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation}, 
      author={Yexing Du and Kaiyuan Liu and Youcheng Pan and Bo Yang and Ming Liu and Bing Qin and Yang Xiang},
      year={2026},
      eprint={2605.28642},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2605.28642}, 
}

@ARTICLE{11481964,
  author={Du, Yexing and Liu, Kaiyuan and Pan, Youcheng and Yang, Bo and Deng, Keqi and Chen, Xie and Xiang, Yang and Liu, Ming and Qin, Bing and Wang, YaoWei},
  journal={IEEE Transactions on Audio, Speech and Language Processing},
  title={MCAT: Scaling Many-to-Many Speech-to-Text Translation With MLLMs to 70 Languages},
  year={2026},
  volume={34},
  pages={2876-2887},
  doi={10.1109/TASLPRO.2026.3684396}
}

@inproceedings{duscalable,
  title={Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion},
  author={Du, Yexing and Pan, Youcheng and Wang, Zekun and Chu, Zheng and Huang, Yichong and Liu, Kaiyuan and Yang, Bo and Xiang, Yang and Liu, Ming and Qin, Bing},
  booktitle={The Fourteenth International Conference on Learning Representations},
  year={2026}
}

@inproceedings{du2025making,
  title={Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning},
  author={Du, Yexing and Pan, Youcheng and Ma, Ziyang and Yang, Bo and Yang, Yifan and Deng, Keqi and Chen, Xie and Xiang, Yang and Liu, Ming and Qin, Bing},
  booktitle={Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={12466--12478},
  year={2025}
}

@article{ma2026slam,
  title={SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing},
  author={Ma, Ziyang and Yang, Guanrou and Chen, Wenxi and Gao, Zhifu and Du, Yexing and Li, Xiquan and Zheng, Zhisheng and Zhu, Haina and Zhuo, Jianheng and Song, Zheshu and others},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  year={2026},
  publisher={IEEE}
}

📄 License

This project is licensed under the CC BY-NC-SA 4.0 license. See the LICENSE file for details.