urhythmic
urhythmic copied to clipboard
Unsupervised Rhythm Modeling for Voice Conversion
Thank you for the amazing work! Regarding the training of HiFi-GAN, how many GPUs did you use? I suspect it might be between 2 to 8 GPUs, but if you...
Hi @bshall, thanks for the great work! I am wondering what is the training data of the pre-trained segmenter, as it is not described in the paper or this repo....
Hi, thanks for sharing great work ! I want to train the model for another language. Should I train a Hubert-soft? If so, should I train a Hubert-discreate from Fairseq...
I have the following use case: I would like train urhythmic to a target speakers voice and do any-to-one voice conversion that ensures the target timbre, but I would like...