Ilvars - Latvian Male VITS Text-to-Speech Model (vers. 2022)

  Autori

Darģis, Roberts and Auziņa, Ilze

  Vienuma identifikators

http://hdl.handle.net/20.500.12574/71

 Izdošanas datums

2022

 Tips

toolService

 Valoda(-s)

Latvian

 Apraksts

A neural model for text-to-speech synthesis in Latvian. Trained using VITS on a 20-hour speech corpus of audiobooks read in a male voice. Currently released for research purposes only.

 Izdevējs

AiLab IMCS UL

 Atbalsts

European Regional Development Fund

Projekta kods: 1.1.1.1/18/A/153

Projekta nosaukums: Latvian Speech Recognition and Synthesis for Medical Applications

 Tēma(-s)

text-to-speech speech synthesis

 Kolekcija (s)

Language resources and tools of AiLab IMCS UL

 

Šo punktu aizstāj ar jaunāku iesniegumu:

http://hdl.handle.net/20.500.12574/89

Visu versiju saraksts  

Rādīt pilnu ierakstu