How to get the "mceps.hdf5" file?

[muvanpersie]

Thank you very much for updating this repo! As you mentioned in the README, the mceps.hdf5 file is converted from VCTK dataset. However, I could not find the mceps.hdf5 file and have no idea how to get it from VCTK. Could you please help me to get it?

[acetylSv]

I used Python-Wrapper-for-World-Vocoder to first extract SPs, APs and f0s acoustic features, and then used pysptk, to transfer SPs to mceps. Hope this two repos solve your problem.

[muvanpersie]

Thanks so much for you reply, I am trying to write a script to convert the wav files to hdf5 files with your advice.

[abuvaneswari]

I used Python-Wrapper-for-World-Vocoder to first extract SPs, APs and f0s acoustic features, and then used pysptk, to transfer SPs to mceps. Hope this two repos solve your problem.

Hello, thanks a lot for making your model available. Your results sound much better than other github vc repositories. Can you kindly share your script that extracts sp, ap, f0 and mceps?

thank you very much.

[acetylSv]

Can you kindly share your script that extracts sp, ap, f0 and mceps?

Hi, the functions I used to extract those features and synthesize them back are here. Hyperparameters are in hyperparams.py.

Or do you need something like this? The code is really in a mess, be sure every line makes sense before you run it lol. I can't guarantee if it's 100% correct.