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

  Authors

Darģis, Roberts and Auziņa, Ilze

  Item identifier

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

 Date issued

2022

 Type

toolService

 Language(s)

Latvian

 Description

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.

 Publisher

AiLab IMCS UL

 Acknowledgement

European Regional Development Fund

Project code: 1.1.1.1/18/A/153

Project name: Latvian Speech Recognition and Synthesis for Medical Applications

 Subject(s)

text-to-speech speech synthesis

 Collection(s)

Language resources and tools of AiLab IMCS UL

 

This item is replaced by a newer submission:

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

List all versions  

Show full item record