Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,8 @@ license: apache-2.0
|
|
| 13 |
## Overview
|
| 14 |
FUTGA is an audio LLM with fine-grained music understanding, learning from generative augmentation with temporal compositions. By leveraging existing music caption datasets and large language models (LLMs), we synthesize detailed music captions with structural descriptions and time boundaries for full-length songs. This synthetic dataset enables FUTGA to identify temporal changes at key transition points, their musical functions, and generate dense captions for full-length songs.
|
| 15 |
|
| 16 |
-
|
| 17 |
-
|
| 18 |
|
| 19 |
## How to load the model
|
| 20 |
We build FUTGA based on [**SALMONN**](https://huggingface.co/tsinghua-ee/SALMONN). Follow the instructions from [**SALMONN**](https://huggingface.co/tsinghua-ee/SALMONN) to load:
|
|
|
|
| 13 |
## Overview
|
| 14 |
FUTGA is an audio LLM with fine-grained music understanding, learning from generative augmentation with temporal compositions. By leveraging existing music caption datasets and large language models (LLMs), we synthesize detailed music captions with structural descriptions and time boundaries for full-length songs. This synthetic dataset enables FUTGA to identify temporal changes at key transition points, their musical functions, and generate dense captions for full-length songs.
|
| 15 |
|
| 16 |
+
<div align=center><img src="fig1.png" height="512px" width="512px"/></div>
|
| 17 |
+
<!--  -->
|
| 18 |
|
| 19 |
## How to load the model
|
| 20 |
We build FUTGA based on [**SALMONN**](https://huggingface.co/tsinghua-ee/SALMONN). Follow the instructions from [**SALMONN**](https://huggingface.co/tsinghua-ee/SALMONN) to load:
|