Closed turian closed 3 years ago
https://github.com/jik876/hifi-gan/issues/46#issuecomment-757593437 The universal model is just a model trained a very large set of data. More speakers = higher quality with unseen speakers. The goal of the universal model is to have a single vocoder that will work well on almost any speaker without retraining.
@CookiePPP Thank you. Do you mind describing what dataset what used for Universal?
It's LJSpeech + VCTK + LibreTTS, all downsampled to 22Khz see https://github.com/jik876/hifi-gan/issues/1
Thanks, would be great to see that in the README
Could you describe a little more what the Universal model is? It's not in the paper or the audio samples. I'm a little confused what it is.