metadata
license: cc-by-4.0
This vits model was trained on the KTH/hungarian-single-speaker-tts dataset.
CSS10 Hungarian: Single Speaker Speech Dataset
The corpus consists of a single speaker, with 4515 segments extracted from this single LibriVox audiobook. It consists about 10 hours of audio data.
Training
The model was trained on a single RTX 3090 GPU. The training took about 3 days.
We created a Hungarian text cleaner function for this dataset, which can be found in the text/cleaners.py file.