Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

Haoning Xu, Zhaoqing Li, Huimeng Wang, Youjun Chen, Chengxi Deng, Mengzhe Geng, Xunying Liu

Thursday at 04:00

4 Views

0 Comments

arXiv:2606.11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducted on the...

Read the full article at the source.

Read Original Article

Was this helpful?