Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ProtoCLR
|
| 2 |
|
| 3 |
This repository contains a CvT-13 [Convolutional Vision Transformer](https://arxiv.org/abs/2103.15808) model trained from scratch on the [Xeno-Canto dataset](https://huggingface.co/datasets/ilyassmoummad/Xeno-Canto-6s-16khz), specifically on 6-second audio segments sampled at 16 kHz. The model is trained on Mel spectrograms of bird sounds using ProtoCLR [(Prototypical Contrastive Loss)](https://arxiv.org/abs/2409.08589) for 300 epochs and can be used as a feature extractor for bird audio classification and related tasks.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- ilyassmoummad/Xeno-Canto-6s-16khz
|
| 5 |
+
pipeline_tag: feature-extraction
|
| 6 |
+
library_name: Pytorch
|
| 7 |
+
tags:
|
| 8 |
+
- Bioacoustics
|
| 9 |
+
---
|
| 10 |
# ProtoCLR
|
| 11 |
|
| 12 |
This repository contains a CvT-13 [Convolutional Vision Transformer](https://arxiv.org/abs/2103.15808) model trained from scratch on the [Xeno-Canto dataset](https://huggingface.co/datasets/ilyassmoummad/Xeno-Canto-6s-16khz), specifically on 6-second audio segments sampled at 16 kHz. The model is trained on Mel spectrograms of bird sounds using ProtoCLR [(Prototypical Contrastive Loss)](https://arxiv.org/abs/2409.08589) for 300 epochs and can be used as a feature extractor for bird audio classification and related tasks.
|