HiFi-GAN icon indicating copy to clipboard operation
HiFi-GAN copied to clipboard

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Results 7 HiFi-GAN issues
Sort by recently updated
recently updated
newest added

Hello, will you be implementing the Wave-UNet-Discriminator from [this paper](https://arxiv.org/pdf/2303.13909.pdf)? My current implementation right now is _very_ unstable. I've only implemented strictly what was written in the paper, so I...

Hi! I've noticed that there is a variable with a wrong (probably just old) name that somehow was left behind. As for hop length - it doesn't really matter in...

Hi, Did you try the idea multiband hifigan?

Is this normal? ![image](https://user-images.githubusercontent.com/65712388/109155509-4d348300-7778-11eb-992c-e13d4e8da177.png)

Got this with your trained model: ``` Traceback (most recent call last): File "inference.py", line 60, in main(args) File "inference.py", line 23, in main model.load_state_dict(checkpoint['model_g']) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1052, in...

Have example of generating mel? did you use tacotron? Thanks you.