Request for separate pretrained HiFiGAN and Autoencoder checkpoints

[hoyeongchoi]

Dear author

First and foremost, I would like to express my appreciation for your work on the AudioLDM project, It is an impressive achievement, and I am genuinely excited to explore its capabilities.

I am writing to inquire if you could kindly provide separate pretrained checkpoints for both the HiFiGAN and the autoencoder models

Thank you for your time and consideration.

[haoheliu]

Hi, thanks for your suggestions. Will add it later today.

[haoheliu]

Hi @hoyeongchoi you can find the VAE and HIFi-GAN checkpoints on Zenodo here: https://zenodo.org/record/7884686#.ZFBb6ezMKbh

[Bai-YT]

Dear authors,

Thank you very much for posting the HiFiGAN checkpoint, and I sincerely appreciate the AudioLDM project. I just hoped to ask if the discriminator of the HiFiGAN can also be shared, as I only found the generator via the link. Thanks for your time!

[Bai-YT]

@haoheliu Sorry for pinging again, but I wondered if the discriminator checkpoint can also be shared for fine-tuning purposes. Thank you very much for helping, and please have a lovely week!