Haohe Liu / 刘濠赫
Haohe Liu / 刘濠赫
Currently the code is mainly for AudioLDM 1.0. Will update the code with AudioLDM 2.0 config later
Yes that's a great idea. LoRA and other adapter is for sure the good direction to go. I'll implement that when I have time or other guys on GitHub may...
Yes a good prompt can usually lead to a better performance.
Oh sorry about that I'll double check
@ntqnhanguyen I found the checkpoint in the tar file. Could you please double check if you are using this link? https://drive.google.com/file/d/1T6EnuAHIc8ioeZ9kB1OZ_WGgwXAVGOZS/view?usp=drive_link
Thank you for the advice. I'll try to make a small sample dataset in the future
Hi @vtsouval. I only implement the PyTorch version. Apology for that.
Thanks @vtsouval for your interest! That would be great! I'm not very familiar with TensorFlow but I'll try my best to help. The experiment section of our paper discusses the...
You can achieve that by correctly configure the yaml file, for example, by only using the CLAP encoders as conditioning signals
Thanks for your contribution. I'll have a review soon