Ilya Shigabeev

> > Small update. StyleMelGAN (1.5M iter) is much better than HiFi-GAN (1.5M iter) as vocoder after FastSpeech2 for my dataset. FS2+StyleMelGAN almost the same quality as FS2+PWG, but SMG...

It doesn't seem to work in my case ``` espeak-ng -x "На горе стоит [[з'амок]]." -v Russian --ipa nə ɡˈorʲi stʌˈit ```

Привет! Я года три не трогал этот проект уже. Но он и не очень легко собирался даже в лучшие времена, скорее всего надо будет ему немного помочь руками. Но идея...

Did you find a solution?

+++

> @lucasnewman Thanks for your hyperparams and pretrained model. It can achieve acceptable results with a batch size of 32 and 100k step on a 4090 GPU. Hey, can you...

> @shigabeev, @lucasnewman has some voice samples in the repo, You should be able to reproduce the same results. If you still need samples let me know, I might be...

@FENRlR do you know by chance the optimal configs for different sampling rates? I need 16kHz, 24kHz and 48kHz.

> I downloaded the model from the web disk you provided, and reported this error when reasoning, do you know how to solve it? RuntimeError: Error(s) in loading state_dict for...

I'm having the same issue ``` root@1c1b2c566ff1:/workspace/ilya_png# python -m bitsandbytes Could not find the bitsandbytes CUDA binary at PosixPath('/usr/local/lib/python3.10/dist-packages/bitsandbytes-0.43.2.dev0-py3.10-linux-x86_64.egg/bitsandbytes/libbitsandbytes_cuda121.so') Could not load bitsandbytes native library: /usr/local/lib/python3.10/dist-packages/bitsandbytes-0.43.2.dev0-py3.10-linux-x86_64.egg/bitsandbytes/libbitsandbytes_cpu.so: cannot open shared object...