We present ESPnet-SpeechLM, an open toolkit designed to democratize the development of speech language models (SpeechLMs) and voice-driven agentic applications. The toolkit standardizes speech processing tasks by framing them as universal sequential modeling problems, encompassing a cohesive workflow of data preprocessing, pre-training, inference, and task evaluation. With ESPnet-SpeechLM, users can easily define task templates and configure key settings, enabling seamless and streamlined SpeechLM development. The toolkit ensures flexibility, efficiency, and scalability by offering highly configurable modules for every stage of the workflow. To illustrate its capabilities, we provide multiple use cases demonstrating how competitive SpeechLMs can be constructed with ESPnet-SpeechLM, including a 1.7B-parameter model pre-trained on both text and speech tasks, across diverse benchmarks. The toolkit and its recipes are fully transparent and reproducible at: https://github.com/espnet/espnet/tree/speechlm.
@article{arxiv.2502.15218,
title = {ESPnet-SpeechLM: An Open Speech Language Model Toolkit},
author = {Jinchuan Tian and Jiatong Shi and William Chen and Siddhant Arora and Yoshiki Masuyama and Takashi Maekaku and Yihan Wu and Junyi Peng and Shikhar Bharadwaj and Yiwen Zhao and Samuele Cornell and Yifan Peng and Xiang Yue and Chao-Han Huck Yang and Graham Neubig and Shinji Watanabe},
journal= {arXiv preprint arXiv:2502.15218},
year = {2025}
}