Ilvars - Latvian Male VITS Text-to-Speech Model (vers. 2023)

  Autori

Darģis, Roberts and Auziņa, Ilze

  Vienuma identifikators

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

 Izdošanas datums

2023

 Tips

toolService

 Valoda(-s)

Latvian

 Apraksts

A neural model for text-to-speech (TTS) synthesis in Latvian. Trained using VITS on a 25-hour speech corpus of audiobooks read in a male voice. Available for academic and non-commercial purposes via an API. To get access to the API, please, send a request to info@ailab.lv.

 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

 

Ministry of Education and Science

Projekta kods: VPP-LETONIKA-2021/1-0006

Projekta nosaukums: Research on Modern Latvian Language and Development of Language Technology

 

Recovery and Resilience Facility

Projekta kods: 2.3.1.1.i.0/1/22/I/CFLA/002

Projekta nosaukums: Language Technology Initiative

 Tēma(-s)

text-to-speech speech synthesis

 Kolekcija (s)

Language resources and tools of AiLab IMCS UL

 Citas versijas

Visu versiju saraksts  

Rādīt pilnu ierakstu