2022 • VITS DANI (using phonemes)
Authors: Daniel Doña Álvarez
Venue: Zenodo
Type: Software
Abstract: VITS model trained in a single speaker dataset in spanish, using phonemes processed with ESpeak-NG Steps: 520K Sample rate: 48kHz
Topics:  N/A
DOI: 10.5281/zenodo.6589880
BIP! social metrics: 0 1
External links: Crossref OpenAIRE
BibTex PDF
We have placed cookies on your device to help make this website and the services we offer better. By using this site, you agree to the use of cookies. Learn more
I accept