Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
```python
|
| 2 |
import torch
|
| 3 |
from transformers import AutoModel
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- audio grounding
|
| 6 |
+
- audio-text retrieval
|
| 7 |
+
- sound-event-detection
|
| 8 |
+
- multimodal
|
| 9 |
+
- clap
|
| 10 |
+
pipeline_tag: feature-extraction
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
# FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining
|
| 15 |
+
FineLAP is a strong contrastively pre-trained audio-language model that excels in both clip- and frame-level audio understanding tasks
|
| 16 |
+
|
| 17 |
```python
|
| 18 |
import torch
|
| 19 |
from transformers import AutoModel
|