dslee2601 commited on
Commit
6fa175c
·
1 Parent(s): 1a2cf86

support cuda

Browse files
README.md CHANGED
@@ -19,7 +19,8 @@ See `requirements.txt`
19
  ```python
20
  from transformers import AutoModel
21
 
22
- model = AutoModel.from_pretrained("hance-ai/audiomae", trust_remote_code=True) # load the pretrained model
 
23
  z = model('path/audio_fname.wav') # (768, 8, 64) = (latent_dim_size, latent_freq_dim, latent_temporal_dim)
24
  ```
25
 
 
19
  ```python
20
  from transformers import AutoModel
21
 
22
+ device = 'cpu' # 'cpu' or 'cuda'
23
+ model = AutoModel.from_pretrained("hance-ai/audiomae", trust_remote_code=True).to(device) # load the pretrained model
24
  z = model('path/audio_fname.wav') # (768, 8, 64) = (latent_dim_size, latent_freq_dim, latent_temporal_dim)
25
  ```
26
 
save_audioMAE_self_sustainable.ipynb CHANGED
The diff for this file is too large to render. See raw diff