tarepan

Thanks for clarification! Someone (like me) could misunderstand this intent/designDecision. Explicit documentation in "Read-only flag" chapter will prevent this unhappy misunderstanding. As feature request, I propose document improvements.

Hi @te0006 I share my results. I am grad if it is good for you. https://tarepan.github.io/UniversalVocoding/ Dataset: total 10 hours utterances Machine: Google Colab T4 others: in GitHub Pages In...

Many reproducible experiments (including this repository) kindly give information of training time. I agree with you and hope papers itself give the information too. Your hearing is correct. Out of...

(Sorry, mistakenly make two same issue... #22)

@todalex thanks for trying this repo! This notebook is for custom dataset. https://github.com/tarepan/Scyclone-PyTorch/blob/main/Scyclone_PyTorch_other_dataset.ipynb I am happy if this help you.

OK, I understand the situation. Can I check our preassumption? If you run the original notebook (https://github.com/tarepan/Scyclone-PyTorch/blob/main/Scyclone_PyTorch_other_dataset.ipynb), does it run correctly?

> Weight_norm is not required for the inference 👍️ You are right! You can do it and it will speed up inference. > in the latest version of Pytorch it...

I am also paying attention to the [VoiceMOS Challenge 2024](https://sites.google.com/view/voicemos-challenge/past-challenges/voicemos-challenge-2024)👀 From the description of UTMOSv2 repository's `README.md`, UTMOSv2 seems to be good! Soon after the publication of preprint papers (UTMOSv2...

Short answer: Yes ## Detailed answer It is depends on Predictor models. The default `utmos22_strong` model support multiple languages (ref: https://github.com/sarulab-speech/UTMOS22/issues/20). In my experience, it works well on English and...