ESPnet-SpeechLM: An Open Speech Language Model Toolkit

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201388" target="_blank" >RIV/00216305:26230/26:0201388 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.naacl-demo.12.pdf" target="_blank" >https://aclanthology.org/2025.naacl-demo.12.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2025.naacl-demo.12" target="_blank" >10.18653/v1/2025.naacl-demo.12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ESPnet-SpeechLM: An Open Speech Language Model Toolkit

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

ESPnet-SpeechLM: An Open Speech Language Model Toolkit

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies: Long Papers, NAACL-HLT 2025

ISBN

9798891761919

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

116-124

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

Hybrid, Albuquerque, New Mexico, USA

Místo konání akce

Hybrid, Albuquerque, NM, USA

Datum konání akce

29. 4. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001598875800012