Use conda:
conda create -p env python=3.11
conda activate ./env
pip install -r requirements.txt
After install all files needed:
python main.py
go to modules folder and type:
git clone https://github.com/yl4579/StyleTTS2.git
cd StyleTTS2
pip install -r requirements.txt
on windows run one more command:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 -U
then install:
pip install phonemizer
on windows install: espeak-ng for windows and set the location at tts.py code:
EspeakWrapper.set_library('C:\Program Files\eSpeak NG\libespeak-ng.dll')