Instructions to use microsoft/wavlm-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/wavlm-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="microsoft/wavlm-base")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("microsoft/wavlm-base") model = AutoModel.from_pretrained("microsoft/wavlm-base") - Notebooks
- Google Colab
- Kaggle
Commit ·
f7a1291
1
Parent(s): 14e28e3
Update preprocessor_config.json
Browse files- preprocessor_config.json +2 -2
preprocessor_config.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"do_normalize":
|
| 3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
| 7 |
-
"return_attention_mask":
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"do_normalize": false,
|
| 3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|