How to use fluxions/vui with Vui:
# !pip install git+https://github.com/fluxions-ai/vui import torchaudio from vui.inference import render from vui.model import Vui, model = Vui.from_pretrained().cuda() waveform = render( model, "Hey, here is some random stuff, usually something quite long as the shorter the text the less likely the model can cope!", ) print(waveform.shape) torchaudio.save("out.opus", waveform[0], 22050)
Is there anyway to adjust the speed ? It talks really fast and doesn't pause for punctuations
Yes if you're using the abraham model, it's definitely quick as he does talk very fast.
We will do pacing control at some point!
· Sign up or log in to comment
