Ilvars - Latvian Male VITS Text-to-Speech Model (vers. 2022)
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.
Result filters
Language
- Latvian (1)
Resource type
- Unspecified (1)
Tool task
- Speech synthesis (1)
- Text-to-speech (1)
Keywords
- speech synthesis (1)
- text-to-speech (1)
Loading...
1 record(s) found