Thodoris Kouzelis
Thodoris Kouzelis
Hi, The results we include in the paper are obtained using AudioLDM with prior preservation loss. Thank you for noticing the bug in the code for AudioLDM2 I will take...
Hi, I'd be glad to set up a Colab session when I have some free time. In the meantime, you can try out all the methods by cloning the repository...
Have you been able to reproduce the training of the multi-scale VQ-VAE with this repo ?[https://github.com/FoundationVision/vaex](https://github.com/FoundationVision/VAR/issues/url)