Code for the paper "FastAdaSP: An Efficient Multitask Inference Framework for Large Speech Language Models". EMNLP 2024 industry track, oral
To be released before Nov.
- Release Code for Qwen-Audio
- Release Code for WavLLM
- Release Evaluation Piepline
@inproceedings{lu-etal-2024-fastadasp,
title = "{F}ast{A}da{SP}: Multitask-Adapted Efficient Inference for Large Speech Language Model",
author = "Lu, Yichen and
Song, Jiaqi and
Yang, Chao-Han Huck and
Watanabe, Shinji",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.33",
pages = "440--451",
}