Team project. More info will be added.
- Install Python 3.7.x
- Install Pytorch:
pip3 install torch==1.8.2+cpu torchvision==0.9.2+cpu torchaudio==0.8.2 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html
- Run
pip install -r requirements.txt
to install the necessary packages. - Install
ffmpeg
. - Download archive with pretrained models for voice cloning from here and unpack them into models.
- Download pretrained model for language classification from here
and unpack it to
model/lang_classification/saved_models/lid.176.ftz
.
Command to start for Linux/MacOS:
export API_TOKEN="TOKEN" && python main.py
Command to start for Windows Powershell:
$env:API_TOKEN = "TOKEN"
python .\main.py