sandslides
Joined 3 years ago
Karma
291
Submissions
10
Member since
Nov 19
Recent submissions
Comment · 8 months ago
Comment · 1 year ago
So Ghostbusters II is now reality? :)
Comment · 2 years ago
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
Comment · 3 years ago
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.
Comment · 3 years ago
The LibriTTS demo clones unseen speakers from a five second or so clip
Comment · 3 years ago
Yes, I noticed that. Doesn't seem right does it
Comment · 3 years ago
Not sure. The only inference demos are colab notebooks. The models are approx 700mb each so I imagine it will run on modest gpu
Comment · 3 years ago
Just tried the collab notebooks. Seems to be very good quality. It also supports voice cloning.
https://en.wikipedia.org/wiki/Hilbert%27s_paradox_of_the_Gra...