🇺🇦 Join Ukrainian Text-to-Speech community: https://t.me/speech_synthesis_uk
Clone the code:
git clone https://github.com/egorsmkv/radtts-waveode
cd radtts-waveodeInstall dependencies:
pip install -r requirements.txtDownload Ukrainian RADTTS and WaveODE models:
mkdir models
cd models
wget https://github.com/egorsmkv/radtts-waveode/releases/download/v1.0/M_105.pth
wget https://github.com/egorsmkv/radtts-istftnet/releases/download/v1.0/RADTTS-Lada.ptThen you can inference own texts by the following command:
python3 inference.py -c config_ljs_dap.json -r models/RADTTS-Lada.pt -t test_sentences.txt --vocoder_path models/M_105.pth --vocoder_config_path waveode_config.yaml -o results/ --sampling_method euler --sampling_steps 20