Markus Toman

Nice.i see you updated the merlin SLT demo "s2" experiment. Perhaps I can free up a couple hours and try it. Is there anything we should be aware of with...

I've noticed that it's really clean now, great. Ran the full demo and the feature extraction is also extremely fast. Also ran the world demo ("s1") again. Here are the...

Hmm I think the quality is pretty good but sounds as if there's more power in the lower frequencies, but signal processing is certainly not my strength so I don't...

Ah yes, I see and try again. Interestingly I found that typically the difference between 6x1024 units vs 6x128 is interestingly not that huge, but never tried to reduce the...

Actually for me adding ! pip install "tensorflow

Just arrived at the same question: the preprocessing in the nvidia taco2 repo is a bit different. Did you finetune on their pretrained LJ model or train a new one...

Generally just stopping at some point and swapping out the data and continuing the training works quite well from my experience.

Interesting, I didn't try with the latest version (and also not for WaveNet), so perhaps something there.

I'm not doing something special. It worked for me in this repo (https://github.com/m-toman/tacorn/tree/fatchord_model - please note the branch, I'm working on the master branch). So it's more or less the...

You are right, I forgot that python holds the script name in argv[0] when I added then len() ifs. Would be nice to replace it with getopts (but you know,...