이준혁(Junhyeok Lee)

Hi! Thank you for your interest! We already wrote code about wav file upsampling (inference) with trained model, but we did not write it on README. https://github.com/mindslab-ai/nuwave/blob/f941928c12db6d0e325e8c1997079d274ea4cede/sampling.py Maybe we could...

Hi! Thank you for the great question! We only tested for x2 and x3, but I think this work also available to apply on non-integer ratio upsampling. You only need...

Thank you for trying the additional experiment! Plz let me know if you need some help!

Interesting works! I expected that you need to train more. Since denoising score matching process is trained by random Gaussian noise and complicated, we also got similar problems. We trained...

In addition, if you have an STT model you could apply conditional score generation suggested by Yang Song (https://arxiv.org/pdf/2011.13456.pdf Section 5 and Appendix I).

Hmm, I think you need to modify the inference schedule instead of the training schedule. Since 8 iteration's value is fit to our setup, maybe it could not be optimal...

(Now I can see it) In my opinion, neural upsampling and accuracy of AST/STT could be irrelevant OR your dataset is small to train general model. If problem is a...

In addition, I am curious about your hyperparameters. Please let me know your batch or audio length or any difference between our [hparameter.yaml](https://github.com/mindslab-ai/nuwave/blob/master/hparameter.yaml) file.

Hello Viet Anh! As already mentioned, since the diffusion model is complicated, it needs a lot of time for training. Our results for targeting 48k was trained over 240k epochs...

Oh sorry for the misinformation. Yeah I mean 240k iterations instead of epoch.