search

haoheliu / AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.
https://audioldm.github.io/
Other
2.43k stars 222 forks source link

AudioLDM-L/-Full weights? #28

Open chavinlo opened 1 year ago

chavinlo commented 1 year ago

Hello, I was reading the paper and noticed a "superior" version of the model, AudioLDM-L are the weights of this version going to be released?

Also, I registered the "audioldm" org on hf, so just let me know if you want it so I can pass it to you

haoheliu commented 1 year ago

If you are interested I can release it next week. Previously I didn't consider releasing it because it's a bit hard to run on a common GPU. Anyway, I can share the weight and will let you know once it's ready.

chavinlo commented 1 year ago

Thanks. I am asking because I plan on finetuning this on some data I got. I use A100s so memory won't be an issue.

galfaroth commented 1 year ago

Thanks. I am asking because I plan on finetuning this on some data I got.

I use A100s so memory won't be an issue.

How can you find-tune it? Do you have a code?

haoheliu commented 1 year ago

@chavinlo please checkout the README for the latest update on model checkpoint

DanahYatim commented 1 year ago

Hi, where can I find the AudioLDM-L/-Full weights? couldn't find on hugging faces.