The initial launch should download the default model.
If there's a problem with the initial download, you can download the needed files from: xTTS-V2 (you need to download: config.json, model.pth, speakers_xtts.pth, vocab.json).
This is how your xtts_model folder should look like :
Training new models is simpler, and it's easier to use languages other than English. Some people prefer the sound of the voice compared to xVASynth. Essentially, it's just an alternative to xVASynth.
4 comments
If there's a problem with the initial download, you can download the needed files from: xTTS-V2 (you need to download: config.json, model.pth, speakers_xtts.pth, vocab.json).
This is how your xtts_model folder should look like :
└── xtts_models/ |
└── v2.0.2/
├── config.json
├── model.pth
├── speakers_xtts.pth
└── vocab.json
It can consume more VRAM to run xTTS compared to xVASynth.
xTTS use around 2-3 GB of VRAM and 5GB of RAM when running on GPU with Deepspeed enable.
You can run on CPU but it will be slower.
This project is inspired by das
You're basically saying to us, "please, DON'T use this!"
What are the positives of this compared to xVASynth?
xVASynth. Essentially, it's just an alternative to xVASynth.