Instructions to use LeBenchmark/wav2vec2-FR-7K-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LeBenchmark/wav2vec2-FR-7K-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="LeBenchmark/wav2vec2-FR-7K-large")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("LeBenchmark/wav2vec2-FR-7K-large") model = AutoModel.from_pretrained("LeBenchmark/wav2vec2-FR-7K-large", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Titouan Parcollet commited on
Commit ·
cc40741
1
Parent(s): 79e893e
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ LeBenchmark provides an ensemble of pretrained wav2vec2 models on different Fren
|
|
| 14 |
|
| 15 |
|
| 16 |
|
| 17 |
-
##
|
| 18 |
|
| 19 |
|
| 20 |
We release four different models that can be found under our HuggingFace organization. Two different wav2vec2 architectures *Base* and *Large* are coupled with our small (1K), medium (3K), and large (7K) corpus. A larger one should come later. In short:
|
|
|
|
| 14 |
|
| 15 |
|
| 16 |
|
| 17 |
+
## Model and data descriptions
|
| 18 |
|
| 19 |
|
| 20 |
We release four different models that can be found under our HuggingFace organization. Two different wav2vec2 architectures *Base* and *Large* are coupled with our small (1K), medium (3K), and large (7K) corpus. A larger one should come later. In short:
|