arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09385cs.SDcs.CLcs.MM
收藏

SLAM-LLM: 一种模块化、开源的多模态大语言模型框架及语音、语言、音频和音乐处理的最佳实践

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing

X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University(X-LANCE实验室,计算机科学学院,人工智能教育部重点实验室,上海交通大学);Tongyi Lab, Alibaba Group(通义实验室,阿里巴巴集团);Peng Cheng Laboratory(鹏城实验室);University of Texas at Austin(德克萨斯大学奥斯汀分校);Tianjin University(天津大学);Hong Kong University of Science and Technology(香港科学大学);Queen Mary University of London(伦敦玛丽女王大学);Nanyang Technological University(南洋理工大学);Shanghai Innovation Institute(上海创新研究院)
Ziyang Ma, Guanrou Yang, Wenxi Chen, Zhifu Gao, Yexing Du, Xiquan Li, Zhisheng Zheng, Haina Zhu, Jianheng Zhuo, Zheshu Song, Ruiyang Xu, Tiranrui Wang, Yifan Ya… 展开作者

Ziyang Ma, Guanrou Yang, Wenxi Chen, Zhifu Gao, Yexing Du, Xiquan Li, Zhisheng Zheng, Haina Zhu, Jianheng Zhuo, Zheshu Song, Ruiyang Xu, Tiranrui Wang, Yifan Yang, Yanqiao Zhu, Zhikang Niu, Liumeng Xue, Yinghao Ma, Ruibin Yuan, Shiliang Zhang, Kai Yu, Eng Siong Chng, Xie Chen

AI总结:

SLAM-LLM是一种开源多模态大语言模型框架,专注于语音、语言、音频和音乐处理,提供模块化配置和高性能检查点以加速研究开发。

摘要:

最近开源多模态大语言模型(MLLM)框架的兴起,如LLaVA,为人工智能开发者和研究人员提供了便捷的开端。然而,大多数MLLM框架主要以视觉作为主要输入模态,并对语音、音频和音乐模态提供有限的深入支持。这种状况阻碍了音频语言模型的发展,并迫使研究人员花费大量精力在代码编写和超参数调优上。我们提出了SLAM-LLM,一种开源的深度学习框架,旨在训练定制化的MLLM,专注于语音、语言、音频和音乐处理。SLAM-LLM提供了不同编码器、投影器、LLM和参数高效微调插件的模块化配置。SLAM-LLM还包含主流任务的详细训练和推理配方,以及高性能的检查点,如基于LLM的自动语音识别(ASR)、自动音频描述(AAC)和音乐描述(MC)。其中一些配方已达到或接近最先进水平,一些相关技术也已获得学术论文的接受。我们希望SLAM-LLM能加速研究人员在迭代、开发、数据工程和模型训练方面的进程。我们致力于通过这一开源框架不断推动基于音频的MLLM,并呼吁社区为基于LLM的语音、音频和音乐处理做出贡献。

英文摘要:

The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and researchers. However, most of the MLLM frameworks take vision as the main input modality, and provide limited in-depth support for the modality of speech, audio, and music. This situation hinders the development of audio-language models, and forces researchers to spend a lot of effort on code writing and hyperparameter tuning. We present SLAM-LLM, an open-source deep learning framework designed to train customized MLLMs, focused on speech, language, audio, and music processing. SLAM-LLM provides a modular configuration of different encoders, projectors, LLMs, and parameter-efficient fine-tuning plugins. SLAM-LLM also includes detailed training and inference recipes for mainstream tasks, along with high-performance checkpoints like LLM-based Automatic Speech Recognition (ASR), Automated Audio Captioning (AAC), and Music Captioning (MC). Some of these recipes have already reached or are nearing state-of-the-art performance, and some relevant techniques have also been accepted by academic papers. We hope SLAM-LLM will accelerate iteration, development, data engineering, and model training for researchers. We are committed to continually pushing forward audio-based MLLMs through this open-source framework, and call on the community to contribute to the LLM-based speech, audio and music processing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑