Instructions to use ylacombe/w2v-bert-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ylacombe/w2v-bert-2.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ylacombe/w2v-bert-2.0")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("ylacombe/w2v-bert-2.0") model = AutoModel.from_pretrained("ylacombe/w2v-bert-2.0") - Notebooks
- Google Colab
- Kaggle
Upload Wav2Vec2BERTForPreTraining
#3
by ylacombe - opened
- config.json +1 -1
config.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"feat_quantizer_dropout": 0.0,
|
| 23 |
"feature_projection_input_dim": 160,
|
| 24 |
"final_dropout": 0.1,
|
| 25 |
-
"hidden_act": "
|
| 26 |
"hidden_dropout": 0.0,
|
| 27 |
"hidden_size": 1024,
|
| 28 |
"initializer_range": 0.02,
|
|
|
|
| 22 |
"feat_quantizer_dropout": 0.0,
|
| 23 |
"feature_projection_input_dim": 160,
|
| 24 |
"final_dropout": 0.1,
|
| 25 |
+
"hidden_act": "swish",
|
| 26 |
"hidden_dropout": 0.0,
|
| 27 |
"hidden_size": 1024,
|
| 28 |
"initializer_range": 0.02,
|