ESPnet-SpeechLM: An Open Speech Language Model Toolkit

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AC8EMQLUH" target="_blank" >RIV/00216208:11320/26:C8EMQLUH - isvavai.cz</a>

Result on the web

<a href="http://arxiv.org/abs/2502.15218" target="_blank" >http://arxiv.org/abs/2502.15218</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2502.15218" target="_blank" >10.48550/arXiv.2502.15218</a>

Result language

angličtina

Original language name

ESPnet-SpeechLM: An Open Speech Language Model Toolkit

Original language description

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.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů