Instructions to use labhamlet/wavjepa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use labhamlet/wavjepa-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="labhamlet/wavjepa-base", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("labhamlet/wavjepa-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files
model.py
CHANGED
|
@@ -137,7 +137,6 @@ class WavJEPA(nn.Module):
|
|
| 137 |
)
|
| 138 |
cur_frames = audio.shape[-1]
|
| 139 |
pad_frames = self.target_length - (cur_frames % self.target_length)
|
| 140 |
-
print(pad_frames)
|
| 141 |
if pad_frames > 0:
|
| 142 |
# Padding with constant 0s
|
| 143 |
pad_arg = (
|
|
|
|
| 137 |
)
|
| 138 |
cur_frames = audio.shape[-1]
|
| 139 |
pad_frames = self.target_length - (cur_frames % self.target_length)
|
|
|
|
| 140 |
if pad_frames > 0:
|
| 141 |
# Padding with constant 0s
|
| 142 |
pad_arg = (
|