Hugging Face's logo

cvssp
/
audioldm-m-full

Diffusers
Safetensors
AudioLDMPipeline
Model card Files Community
3
sanchit-gandhi commited on
Commit
77e8492
·
1 Parent(s): 41aa0c4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -54,7 +54,7 @@ used to load pre-trained weights and generate text-conditional audio outputs:
54
  from diffusers import AudioLDMPipeline
55
  import torch
56
 
57
- repo_id = "cvssp/audioldm-s-v2"
58
  pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
59
  pipe = pipe.to("cuda")
60
 
 
54
  from diffusers import AudioLDMPipeline
55
  import torch
56
 
57
+ repo_id = "cvssp/audioldm-m-full"
58
  pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
59
  pipe = pipe.to("cuda")
60