This repository provides an implementation of a Speaker-Attributed Automatic Speech Recognition model. The model performs both multilingual speech recognition and speaker embedding extraction, enabling speaker differentiation.
@misc{nguyen2025msaasrefficientmultilingualspeaker,
title={MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models},
author={Thai-Binh Nguyen and Alexander Waibel},
year={2025},
eprint={2411.18152},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2411.18152},
}
License
CC-BY-NC 4.0
Contact
Contributions are welcome; feel free to create a PR or email me:
[Binh Nguyen](nguyenvulebinh[at]gmail.com)
Runs of nguyenvulebinh MSA-ASR on huggingface.co
13
Total runs
-1
24-hour runs
0
3-day runs
3
7-day runs
10
30-day runs
More Information About MSA-ASR huggingface.co Model
MSA-ASR huggingface.co
MSA-ASR huggingface.co is an AI model on huggingface.co that provides MSA-ASR's model effect (), which can be used instantly with this nguyenvulebinh MSA-ASR model. huggingface.co supports a free trial of the MSA-ASR model, and also provides paid use of the MSA-ASR. Support call MSA-ASR model through api, including Node.js, Python, http.
MSA-ASR huggingface.co is an online trial and call api platform, which integrates MSA-ASR's modeling effects, including api services, and provides a free online trial of MSA-ASR, you can try MSA-ASR online for free by clicking the link below.
nguyenvulebinh MSA-ASR online free url in huggingface.co:
MSA-ASR is an open source model from GitHub that offers a free installation service, and any user can find MSA-ASR on GitHub to install. At the same time, huggingface.co provides the effect of MSA-ASR install, users can directly use MSA-ASR installed effect in huggingface.co for debugging and trial. It also supports api for free installation.