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)
-
- Citas versijas
-
