DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huo, Yanru, Jiang, Ziyue, Tang, Zuoli, Hong, Qingyang, Zhao, Zhou
Format:	Preprint
Published:	2025
Subjects:	Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.09748