tt-vae-gan
Timbre transfer with variational autoencoding and cycle-consistent adversarial networks. Able to transfer the timbre of an audio source to that of another. (by RussellSB)
CoGAN
By mingyuliutw
tt-vae-gan | CoGAN | |
---|---|---|
4 | 1 | |
64 | 284 | |
- | - | |
1.8 | 0.0 | |
over 2 years ago | over 6 years ago | |
Python | Jupyter Notebook | |
- | - |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tt-vae-gan
Posts with mentions or reviews of tt-vae-gan.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-12-25.
- Use deep fake tech to say stuff with your favorite characters
-
[Project] I've successfully applied a VAE-GAN model (initially for voice conversion ) to the problem of timbre transfer between musical instruments. This showcases the generalisability of the approach with the potential for more than just one audio style transfer problem.
Link for demonstration, code, and tutorial: https://github.com/RussellSB/tt-vae-gan
-
[P] Voice Conversion VAE-Cycle-GAN on Melspectrograms
I've been working on an open source implementation for the past month. The link for it can be found here. But have since been struggling with a load of mode collapse - or the model outputting "blurry" spectrograms not quite capturing the same initial structure as they should.
CoGAN
Posts with mentions or reviews of CoGAN.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-04-15.
-
[P] Voice Conversion VAE-Cycle-GAN on Melspectrograms
You also set biases to false? At least in CoGAN there are biases. https://github.com/mingyuliutw/CoGAN/blob/master/cogan/models/celeba/celeba.train.ptt
What are some alternatives?
When comparing tt-vae-gan and CoGAN you can also consider the following projects:
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
PyTorch-GAN - PyTorch implementations of Generative Adversarial Networks.
YourTTS - YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
StarGANv2-VC - StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
autovc - AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
voice_conversion