AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ganguly, Shreyan, Nayak, Roshan, Rao, Rakshith, Deb, Ujan, AP, Prathosh
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.08019