first
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ tags:
|
|
| 13 |
- audio-text
|
| 14 |
---
|
| 15 |
# Mellow
|
| 16 |
-
[[`Paper`]()] [[`GitHub`](https://github.com/soham97/Mellow)] [[`Checkpoint`](https://huggingface.co/soham97/Mellow)]
|
| 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 |
|
|
@@ -43,8 +43,8 @@ python example.py
|
|
| 43 |
|
| 44 |
## Usage
|
| 45 |
The MellowWrapper class allows easy interaction with the model. To use the wrapper, inputs required are:
|
| 46 |
-
- `config`: The option supported is "
|
| 47 |
-
- `model`: The option supported is "v0
|
| 48 |
- `examples`: List of examples. Each example is a list containing three entries: audiopath1, audiopath2, prompt
|
| 49 |
|
| 50 |
Supported functions:
|
|
|
|
| 13 |
- audio-text
|
| 14 |
---
|
| 15 |
# Mellow
|
| 16 |
+
[[`Paper`]()] [[`GitHub`](https://github.com/soham97/Mellow)] [[`🤗Checkpoint`](https://huggingface.co/soham97/Mellow)] [[`Zenodo`](https://huggingface.co/soham97/Mellow)]
|
| 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 |
|
|
|
|
| 43 |
|
| 44 |
## Usage
|
| 45 |
The MellowWrapper class allows easy interaction with the model. To use the wrapper, inputs required are:
|
| 46 |
+
- `config`: The option supported is "v0"
|
| 47 |
+
- `model`: The option supported is "v0"
|
| 48 |
- `examples`: List of examples. Each example is a list containing three entries: audiopath1, audiopath2, prompt
|
| 49 |
|
| 50 |
Supported functions:
|