readme update
Browse files- README.md +1 -2
- config.json +0 -0
README.md
CHANGED
|
@@ -13,7 +13,7 @@ tags:
|
|
| 13 |
- audio-text
|
| 14 |
---
|
| 15 |
# Mellow
|
| 16 |
-
[[
|
| 17 |
|
| 18 |
Mellow is a small Audio-Language Model that takes in two audios and a text prompt as input and produces free-form text as output. It is a 167M parameter model and trained on ~155 hours of audio (AudioCaps and Clotho), and achieves SoTA performance on different tasks with 50x fewer parameters.
|
| 19 |
|
|
@@ -62,7 +62,6 @@ from mellow import MellowWrapper
|
|
| 62 |
# setup cuda and device
|
| 63 |
cuda = torch.cuda.is_available()
|
| 64 |
device = 0 if cuda else "cpu"
|
| 65 |
-
mellow = Mellow(config="<choice of config>", model_path="<model weights", device=device, cuda=cuda)
|
| 66 |
|
| 67 |
# setup mellow
|
| 68 |
mellow = MellowWrapper(
|
|
|
|
| 13 |
- audio-text
|
| 14 |
---
|
| 15 |
# Mellow
|
| 16 |
+
[[`📑Paper`]()] [[`⚙️GitHub`](https://github.com/soham97/Mellow)] [[`🤗Checkpoint`](https://huggingface.co/soham97/Mellow)] [[`📊Zenodo`](https://zenodo.org/records/15002886)]
|
| 17 |
|
| 18 |
Mellow is a small Audio-Language Model that takes in two audios and a text prompt as input and produces free-form text as output. It is a 167M parameter model and trained on ~155 hours of audio (AudioCaps and Clotho), and achieves SoTA performance on different tasks with 50x fewer parameters.
|
| 19 |
|
|
|
|
| 62 |
# setup cuda and device
|
| 63 |
cuda = torch.cuda.is_available()
|
| 64 |
device = 0 if cuda else "cpu"
|
|
|
|
| 65 |
|
| 66 |
# setup mellow
|
| 67 |
mellow = MellowWrapper(
|
config.json
ADDED
|
File without changes
|