SNIPER Training: Single-Shot Sparse Training for Text-to-Speech

Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models can improve on dense models via pruning and extra retraining, or converge faster than dense models with some performance loss.

Data and Resources

Cite this as

Perry Lam, Huayun Zhang, Nancy F. Chen, Berrak Sisman, Dorien Herremans (2024). Dataset: SNIPER Training: Single-Shot Sparse Training for Text-to-Speech. https://doi.org/10.57702/n0bfbu9z

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Perry Lam
More Authors
Huayun Zhang
Nancy F. Chen
Berrak Sisman
Dorien Herremans
Homepage https://github.com/iamanigeeit/sniper