Brandon Thomas

@durch Not sure what your bandwidth looks like, but I'd be happy to pay a bug bounty to have this fixed. 🥺 🙏 Totally understand if there isn't any time...

@seantempesta here's my fork: https://github.com/ml-applications/melgan-seungwonpark It doesn't add much. The only valuable thing here is probably the `requirements.txt`. I've added some automation scripts, but I'm moving to Dockerize everything as...

Could you share your results? My results are a bit robotic too, but gone off the supported path and modified the network to train on multiple speakers via `n_speakers` and...

@jaywalnut310 , do you have any updates with your current experiments? I'm using your model very successfully in production and am very invested in its development. I would love to...

Thanks so much for the feedback! 256 dimensions performs much better as far as I can tell. It's perhaps a little premature to report my findings, but I've performed the...

Add these two hparams: ``` "n_speakers": 10, "gin_channels": 16 ``` I'm not sure what the ideal value for `gin_channels` is to get a rich embedding, and I asked in another...

🤦‍♂ I just saw the platform flags in the code and that that Mac support is listed as TODO in the README.

Thanks for the super responsive answer! This is already an incredibly valuable crate and I appreciate the functionality already available on Linux. Depending on the direction my work takes me...

@kotx this should work with a more recent version of rustls. We've managed to upgrade and connect via IP address.

I'll pay a bounty (~$500) to whomever lands `opus` / `e1a70095c4409478c1ded499fb8dd4afa540fb90`. This is important for dealing with web uploads as browser APIs use opus. Bonus points if media duration is...