first commit
Browse files
README.md
CHANGED
|
@@ -68,4 +68,19 @@ prompt = "Rolling thunder with lightning strikes"
|
|
| 68 |
output = pipeline(prompt=prompt, num_inference_steps=100, guidance_scale=7.5)
|
| 69 |
audio = output.audios[0]
|
| 70 |
IPython.display.Audio(data=audio, rate=16000)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
```
|
|
|
|
| 68 |
output = pipeline(prompt=prompt, num_inference_steps=100, guidance_scale=7.5)
|
| 69 |
audio = output.audios[0]
|
| 70 |
IPython.display.Audio(data=audio, rate=16000)
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
## Citation
|
| 75 |
+
|
| 76 |
+
Please consider citing the following article if you found our work useful:
|
| 77 |
+
|
| 78 |
+
```bibtex
|
| 79 |
+
@article{xue2024auffusion,
|
| 80 |
+
title={Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation},
|
| 81 |
+
author={Jinlong Xue and Yayue Deng and Yingming Gao and Ya Li},
|
| 82 |
+
journal={arXiv preprint arXiv:2401.01044},
|
| 83 |
+
year={2024}
|
| 84 |
+
}
|
| 85 |
+
```
|
| 86 |
```
|