Denoising Diffusion Probabilistic Models for SpeechBrain#1599
Merged
mravanelli merged 179 commits intospeechbrain:developfrom Aug 13, 2023
Merged
Denoising Diffusion Probabilistic Models for SpeechBrain#1599mravanelli merged 179 commits intospeechbrain:developfrom
mravanelli merged 179 commits intospeechbrain:developfrom
Conversation
…hbrain into diffusion-direct
Change spec_norm_std to 1 Change annealing to WarmCoolDecayLRSchedule
…hbrain into diffusion-direct
BenoitWang
reviewed
Jul 31, 2023
Collaborator
There was a problem hiding this comment.
I just re-ran the fastspeech training to check the shapes and I found squeeze(-1) is correct. Everything works fine, thanks @flexthink, a good catch!
mravanelli
approved these changes
Aug 13, 2023
Collaborator
|
I did extensive tests. I ran the full diffusion recipes. Everything looks good to me now. The quality of the digit generated with diffusion is pretty high, considering that AudioMNIST is a small dataset. Only the quality of latent diffusion is quite low, but I think we can improve it in another PR. Thank you @flexthink and @BenoitWang for this great work! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains a basic implementation of Denoising Diffusion Probabilistic Models (DDPM) for SpeechBrain
https://arxiv.org/pdf/2006.11239.pdf
An example is provided to generate MEL-spectrograms using the AudioMNIST dataset
It also contains an implementation of DiffWave by @BenoitWang