Hello,
I am trying to finetune CLAP for a audio to text retrieval task, and I have formatted the datasets accordingly. I am facing issue to load the pretrained ckpts. I understand that the pretrained ckpt is loaded from the --pretrained arg but the model additionally needs a --amodel flag. How do I know which pretrained ckpt corresponds to which amodel?
Hello,
I am trying to finetune CLAP for a audio to text retrieval task, and I have formatted the datasets accordingly. I am facing issue to load the pretrained ckpts. I understand that the pretrained ckpt is loaded from the --pretrained arg but the model additionally needs a --amodel flag. How do I know which pretrained ckpt corresponds to which amodel?