Skip to content

Conversation

xcmyz
Copy link

@xcmyz xcmyz commented Sep 16, 2022

No description provided.

nn.init.zeros_(self.output_projection.weight)

def forward(self, audio, diffusion_step, spectrogram=None):
def forward(self, audio, diffusion_step, spectrogram=None, infer=False):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Excellent change - thanks for sending a PR.

Instead of adding a boolean flag, can we have both the training and inference code run the upsampler before passing it in?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants