naver-ai/USDM-DailyTalk

Model

Model Card

1

2 commits

1 linked in READMEs

updated Nov 28, 2024

See the code

README

Model Card

Unified Spoken Dialog Model (USDM), a model obtained by supervised fine-tuning the Unified Speech-Text Model (USTM) on the DailyTalk dataset, preprocessed into single-turn conversations.

Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation [NeurIPS 2024]

BibTeX

@inproceedings{
  kim2024paralinguisticsaware,
  title={Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation},
  author={Heeseung Kim and Soonshin Seo and Kyeongseok Jeong and Ohsung Kwon and Soyoon Kim and Jungwhan Kim and Jaehong Lee and Eunwoo Song and Myungwoo Oh and Jung-Woo Ha and Sungroh Yoon and Kang Min Yoo},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024},
  url={https://openreview.net/forum?id=NjewXJUDYq}
}
audio-to-audio
endpoints_compatible
mistral
safetensors
text-generation
text-generation-inference
transformers

naver-ai/USDM-DailyTalk

Model

Model Card

1

2 commits

1 linked in READMEs

updated Nov 28, 2024

See the code

README

Model Card

Unified Spoken Dialog Model (USDM), a model obtained by supervised fine-tuning the Unified Speech-Text Model (USTM) on the DailyTalk dataset, preprocessed into single-turn conversations.

Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation [NeurIPS 2024]

BibTeX

@inproceedings{
  kim2024paralinguisticsaware,
  title={Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation},
  author={Heeseung Kim and Soonshin Seo and Kyeongseok Jeong and Ohsung Kwon and Soyoon Kim and Jungwhan Kim and Jaehong Lee and Eunwoo Song and Myungwoo Oh and Jung-Woo Ha and Sungroh Yoon and Kang Min Yoo},
  booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year={2024},
  url={https://openreview.net/forum?id=NjewXJUDYq}
}
audio-to-audio
endpoints_compatible
mistral
safetensors
text-generation
text-generation-inference
transformers