Data · dataset · 2025
Ilvars - Latvian Male VITS Text-to-Speech Model (vers. 2023)
Listed in DataverseLV
A neural model for text-to-speech (TTS) synthesis in Latvian.
Description
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.
Links
Where it is published
- Dataverse dataset page dv.dataverse.lv/dataset.xhtml?persistentId=hdl%3A20.500.12574%2F89 ↗
landing page · from dv dataverse lv
- Persistent identifier hdl.handle.net/20.500.12574/89 ↗
DOI / persistent id · from dv dataverse lv
Catalogue records · 1
- Dataverse API dv.dataverse.lv/api/datasets/:persistentId/?persistentId=hdl%3A20.500.12574%2F… ↗
metadata API · from dv dataverse lv
Topics
- Inferred from text
- Audio 65%
Provenance · 1 source records, 6 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| DataverseLV | hdl:20.500.12574/89 | 14 h ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[modality].local:modality:audio | enrichment · dv dataverse lv | keyword-concept-rules@1.0.0 | title+description (65%) |
| created_date | source · dv dataverse lv | connector:dv_dataverse_lv@1.0.0 | |
| description | source · dv dataverse lv | connector:dv_dataverse_lv@1.0.0 | /description |
| publication_date | source · dv dataverse lv | connector:dv_dataverse_lv@1.0.0 | |
| title | source · dv dataverse lv | connector:dv_dataverse_lv@1.0.0 | /name |
| updated_date | source · dv dataverse lv | connector:dv_dataverse_lv@1.0.0 |