sandslides

could I just leave my favourite thing ever here? thanks :)

https://en.wikipedia.org/wiki/Hilbert%27s_paradox_of_the_Gra...

So Ghostbusters II is now reality? :)

The model weights have been uploaded to Huggingface : https://huggingface.co/pyp1/VoiceCraft

This seems to be really high quality judging by the demo's. Not had time to try it for myself

Demos : https://jasonppy.github.io/VoiceCraft_web/

The speech generated is the best I've heard from an open source model. The one test I made didn't make an exact clone either but this is still early days. There's likely something not quite right. The cloned voice does speak without any artifacts or other weirdness that most TTS systems suffer from.

The LibriTTS demo clones unseen speakers from a five second or so clip

Yes, I noticed that. Doesn't seem right does it

Not sure. The only inference demos are colab notebooks. The models are approx 700mb each so I imagine it will run on modest gpu

Just tried the collab notebooks. Seems to be very good quality. It also supports voice cloning.