0

There is a post How can I run Mozilla TTS/Coqui TTS training with CUDA on a Windows system? answered by GuyPaddock, but I have RTX a5000 graphic card, running Windows 10. I'm not a programmer, but I think it needs CUDA version 11.x for this card. I am seeking a guide about what I should install to be able to run it and train models. It's best not to mess with the webUI from AUTOMATIC1111, which requires Python 3.10.6.

I am trying to install it from the link above and also from YouTube. I am trying to install this on Python 3.10.8 because stable diffusion needs Python 3.10.6, and version 3.10.8 is from October like CUDA 11.8. What do I need to do to make it work?

halfer
  • 19,824
  • 17
  • 99
  • 186
matbardeli
  • 1

1 Answers1

1

I just successfully installed Coqui TTS on windows using Anaconda. I am not going to give an overly detailed guide, but I will list the major actions to get it running. First install Anaconda (and learn to use it) and Gitbash. Use gitbash (or some other method) to clone the TTS git.

conda create -n coquitts python=3.10
conda activate coquitts
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
cd (directory of tts)
pip install -r requirements.txt
python setup.py develop
#use python script to produce tts results
python (YourScriptHere).py

An example of a python script is available on the github page. With a little alteration you should be able to get it to work for you. Don't give up. This might take you some serious effort depending on your knowledge of using these tools.

mr.roboto
  • 11
  • 3