-
I'm currently reworking the general training procedure to more easily enable
- [x] use your own dataset (only have to provide a metadata.csv in the correct format)
- [x] pick a pretrained model …
-
Hey, thanks for your work in this project, it is really good.
I'm trying to use this vocoder to generate wavs from magnitude spectrograms I generated using another neural network. Using griffin-lim…
-
Just a few updates around LPCNet. The repo has been transferred from the mozilla organization to xiph. Everything should just keep working (let us know if it doesn't) as usual.
Recently there have…
-
when I'm trying to run voicefixer, I'm getting these messages:
Downloading the weight of neural vocoder: TFGAN
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versio…
-
## 🚀 Feature
Add support for 8bit conv_transpose inference operators in the form of torch.nn.quantized.functional.conv_transpose1d/2d/3d.
## Motivation
I haven't seen this mentioned elsewhere …
-
Observing that there is no mature data preprocessing in this project, which directly uses raw data for training, we propose to add data preprocessing
-
## Describe the bug
In [models/base/new_inference.py](https://github.com/open-mmlab/Amphion/blob/57ec89cecb0fa6097d13471a03a6545145221265/models/base/new_inference.py#L145C5-L145C5)
`vocoder_cfg, …
-
Is there any instruction about prepare the training data?
Thanks for spending your time on my issue.
I appreciate it.
-
-
Neural audio synthesis models are hard to compare automatically - a survey will be needed to show that the quality didn't decrease through our speedups