search

lucidrains / naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
MIT License
1.26k stars 100 forks source link

example model #13

Closed azulika closed 1 year ago

azulika commented 1 year ago

Thanks for your work. Are there any pre-trained models (.pt) for this project? If not, do you plan to provide them? It would be great if there were models available to check how this project works.

Curlypla commented 1 year ago

As mentioned in the previous issues, the project is in WIP and therefore trained is not even really possible yet. Once the project reaches a trainable stage, a lot of experimentation will have to be done and these trainings will take some time

a897456 commented 5 months ago

Thanks for your work. Are there any pre-trained models (.pt) for this project? If not, do you plan to provide them? It would be great if there were models available to check how this project works.

image I completed the training of 100k steps and got the .pt file which includes 5 items, but I don't know how to use it