Checkpoints for pruned and Unpruned (baseline) AudioLDM-M-Full model

The files contain checkpoints of pruned and original text-to-audio generation model, AudioLDM-M-Full.  The codes associated with the checkpoints are included here:  Github Link.

A description of attached files is below:

1. audioldm-m-full.ckpt: pre-trained AudioLDM-M-Full checkpoint
2. Unet_model-m.ckpt : pre-trained U-Net model checkpoint
3.  l1_audioldm-m-full_p1.ckpt: Pruned checkpoints, with b4 (or p) = 1, {b1,b2,b3} = {1,2,3}
4.   l1_audioldm-m-full_p1_dp1.ckpt: Pruned checkpoints, with b4 (or p) = 1, b3 (or dp) =1,  {b1,b2} = {1,2}
5. l1_audioldm-m-full_p2_dp2.ckpt: Pruned checkpoints, with b4 (or p) = 2, b3 (or dp) =2,  {b1,b2} = {1,2}
6. sorted_indexes_dict.pkl: sorted indxes across convolutional layers of U-Net using $l_1$-norm based pruning method.