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

 
CLARIN Centre of Latvian language resources and tools
  Authors
Darģis, Roberts
  Item identifier
http://hdl.handle.net/20.500.12574/89
 Date issued
2023
 Type
toolService
 Language(s)
Latvian
 Description
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. 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

 

Ministry of Education and Science

Project code: VPP-LETONIKA-2021/1-0006

Project name: Research on Modern Latvian Language and Development of Language Technology

 Subject(s)
text-to-speech speech synthesis
 Collection(s)
Language resources and tools of AiLab IMCS UL
 Other versions
Show full item record
 

 Files in this item

This item is
Publicly Available
and licensed under:
Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Icon
Name
VITS_Latvian_2023.zip
Size
376.17 MB
Format
application/zip
Description
see README
MD5
e8ea23f027e24fbcd92153c4cfddb292
 Download file  Preview
 File Preview  
  • VITS_Latvian_2023
    • Latvian.json-1 B
    • README.md-1 B
    • symbols.py-1 B
    • VITS_Latvian_G.pth-1 B
    • phoneme_map.tsv-1 B
  • __MACOSX
    • VITS_Latvian_2023
      • ._README.md-1 B
      • ._Latvian.json-1 B
      • ._VITS_Latvian_G.pth-1 B
      • ._symbols.py-1 B
      • ._phoneme_map.tsv-1 B
    • ._VITS_Latvian_2023-1 B

Partners, Coordination, Funding

Repository

More

Activities of CLARIN Latvia are supported by project of the European Regional Development Fund Nr. 1.1.1.5/18/I/016 University of Latvia and institutes in the European Research Area - Excellency, activity, mobility, capacity.

This platform runs under the software developed for the LINDAT/CLARIN repository for linguistics , available on GitHub