metadata
license: cc-by-4.0
datasets:
- KTH/hungarian-single-speaker-tts
language:
- hu
tags:
- text-to-speech
- audio
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 1 day for the first checkpoint (Step 93000). Based on the quality of the preview model, we are aiming for 250K Steps.
We created a Hungarian text cleaner function for this dataset, which can be found in the text/cleaners.py file.