Show simple item record

 
dc.contributor.author Darģis, Roberts
dc.contributor.author Auziņa, Ilze
dc.date.accessioned 2022-11-30T16:04:11Z
dc.date.available 2022-11-30T16:04:11Z
dc.date.issued 2022
dc.identifier.uri http://hdl.handle.net/20.500.12574/71
dc.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.
dc.language.iso lav
dc.publisher AiLab IMCS UL
dc.relation.isreplacedby http://hdl.handle.net/20.500.12574/89
dc.rights CLARIN RESTRICTED
dc.rights.uri https://www.kielipankki.fi/lic/example-license-clarin-res-id-by-plan-priv-nored-other-current/
dc.rights.label RES
dc.subject text-to-speech
dc.subject speech synthesis
dc.title Ilvars - Latvian Male VITS Text-to-Speech Model (vers. 2022)
dc.type toolService
metashare.ResourceInfo#ContentInfo.detailedType tool
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent true
has.files yes
branding CLARIN Centre of Latvian language resources and tools
contact.person Normunds Grūzītis normunds.gruzitis@lumii.lv Institute of Mathematics and Computer Science, University of Latvia
sponsor European Regional Development Fund 1.1.1.1/18/A/153 Latvian Speech Recognition and Synthesis for Medical Applications Other
files.size 394444635
files.count 1


 Files in this item

This item is
Restricted Use
and licensed under:
CLARIN RESTRICTED
Inform Before Use Noncommercial No Derivative Works
Icon
Name
VITS_Latvian.zip
Size
376.17 MB
Format
application/zip
Description
a TTS model and its usage instructions
MD5
eb12e9cfd3f86ba8adda9d0958f489c7
 Download file

Show simple item record