VITS TTS model fitted for lithuanian language.
This project uses conda for virtual environment and package management.
conda env create -f environment.ymlconda activate vits
Training required GPU with CUDA support!
Download the training dataset, then rename or create a link to the dataset folder: ln -s files/datasets/atrinkti_sak_3/wav DUMMY1
Run the following command to start training:
python train.py -c files/configs/lt.json -m lithuanianDataset is not added in this repository since it is quite big and github charges for LFS usage if reached certain size treshold
To test trained model you can use inference.ipynb notebook in notebooks directory. To use trained model parameters replace load_checkpoint with trained model path from logs directory