update readme
Browse files
README.md
CHANGED
|
@@ -20,13 +20,7 @@ pipeline_tag: feature-extraction
|
|
| 20 |
FineLAP is a strong contrastively pre-trained audio-language model that excels in both clip- and frame-level audio understanding tasks
|
| 21 |
|
| 22 |
|
| 23 |
-
<div align="center">
|
| 24 |
-
<img src="resources/radar_performance.png" alt="Radar performance" width="46%">
|
| 25 |
-
<img src="resources/sed_result_Y5J603SAj7QM_210.000_220.000.png" alt="SED result" width="50.5%">
|
| 26 |
-
</div>
|
| 27 |
|
| 28 |
-
|
| 29 |
-
<br>
|
| 30 |
You can use the script below to extract frame- and clip-level features or calculate similarity:
|
| 31 |
|
| 32 |
```python
|
|
|
|
| 20 |
FineLAP is a strong contrastively pre-trained audio-language model that excels in both clip- and frame-level audio understanding tasks
|
| 21 |
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
|
|
|
|
|
|
| 24 |
You can use the script below to extract frame- and clip-level features or calculate similarity:
|
| 25 |
|
| 26 |
```python
|