Update README.md
Browse filesadd repo & training datasets
README.md
CHANGED
|
@@ -17,7 +17,13 @@ This repo contains the config & pretrained weights of the model described in the
|
|
| 17 |
[[arXiv page](https://arxiv.org/abs/2309.17352)]
|
| 18 |
## GitHub Repository
|
| 19 |
To use this model, please refer to our code published at:
|
| 20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## BibTex
|
| 22 |
If you find our model useful, please consider citing our paper. Thanks!
|
| 23 |
```
|
|
|
|
| 17 |
[[arXiv page](https://arxiv.org/abs/2309.17352)]
|
| 18 |
## GitHub Repository
|
| 19 |
To use this model, please refer to our code published at:
|
| 20 |
+
- https://github.com/slSeanWU/beats-conformer-bart-audio-captioner
|
| 21 |
+
## Training Data
|
| 22 |
+
- Pretrain
|
| 23 |
+
- **AudioCaps**: https://github.com/cdjkim/audiocaps/tree/master
|
| 24 |
+
- **ChatGPT mix-ups from Clotho**: https://huggingface.co/datasets/slseanwu/clotho-chatgpt-mixup-50K
|
| 25 |
+
- Finetune
|
| 26 |
+
- **Clotho (V2)**: https://zenodo.org/records/4783391
|
| 27 |
## BibTex
|
| 28 |
If you find our model useful, please consider citing our paper. Thanks!
|
| 29 |
```
|