Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ ECAPA2 is a hybrid neural network architecture and training strategy for speaker
|
|
| 15 |
|
| 16 |
### Download model
|
| 17 |
|
| 18 |
-
You need to install the huggingface_hub package to download the ECAPA2 model:
|
| 19 |
|
| 20 |
```bash
|
| 21 |
pip install --upgrade huggingface_hub
|
|
@@ -49,7 +49,7 @@ embedding = ecapa2_model(audio)
|
|
| 49 |
|
| 50 |
### Hierarchical Feature Extraction
|
| 51 |
|
| 52 |
-
For the extraction of other hierachical features, the
|
| 53 |
|
| 54 |
```python
|
| 55 |
# only extracts embedding, same as previous example
|
|
|
|
| 15 |
|
| 16 |
### Download model
|
| 17 |
|
| 18 |
+
You need to install the `huggingface_hub` package to download the ECAPA2 model:
|
| 19 |
|
| 20 |
```bash
|
| 21 |
pip install --upgrade huggingface_hub
|
|
|
|
| 49 |
|
| 50 |
### Hierarchical Feature Extraction
|
| 51 |
|
| 52 |
+
For the extraction of other hierachical features, the `label` argument can be used, which accepts a string containing the feature ids separated with '|':
|
| 53 |
|
| 54 |
```python
|
| 55 |
# only extracts embedding, same as previous example
|