Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,48 @@ tags:
|
|
| 12 |
---
|
| 13 |
# Model Overview
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
## Description:
|
| 16 |
Audio Flamingo 3 (AF3) is a fully open, state-of-the-art Large Audio-Language Model (LALM) that advances reasoning and understanding across speech, sounds, and music. AF3 builds on previous work with innovations in:
|
| 17 |
|
|
|
|
| 12 |
---
|
| 13 |
# Model Overview
|
| 14 |
|
| 15 |
+
<div align="center" style="display: flex; justify-content: center; align-items: center; text-align: center;">
|
| 16 |
+
<a href="https://github.com/NVIDIA/audio-flamingo" style="margin-right: 20px; text-decoration: none; display: flex; align-items: center;">
|
| 17 |
+
<img src="static/logo-no-bg.png" alt="Audio Flamingo 3 🔥🚀🔥" width="120">
|
| 18 |
+
</a>
|
| 19 |
+
</div>
|
| 20 |
+
<div align="center" style="display: flex; justify-content: center; align-items: center; text-align: center;">
|
| 21 |
+
<h2>
|
| 22 |
+
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio-Language Models
|
| 23 |
+
</h2>
|
| 24 |
+
</div>
|
| 25 |
+
|
| 26 |
+
<div align="center" style="display: flex; justify-content: center; margin-top: 10px;">
|
| 27 |
+
<a href=""><img src="https://img.shields.io/badge/arXiv-2503.03983-AD1C18" style="margin-right: 5px;"></a>
|
| 28 |
+
<a href="https://research.nvidia.com/labs/adlr/AF3/"><img src="https://img.shields.io/badge/Demo page-228B22" style="margin-right: 5px;"></a>
|
| 29 |
+
<a href="https://github.com/NVIDIA/audio-flamingo"><img src='https://img.shields.io/badge/Github-Audio Flamingo 3-9C276A' style="margin-right: 5px;"></a>
|
| 30 |
+
<a href="https://github.com/NVIDIA/audio-flamingo/stargazers"><img src="https://img.shields.io/github/stars/NVIDIA/audio-flamingo.svg?style=social"></a>
|
| 31 |
+
</div>
|
| 32 |
+
|
| 33 |
+
<div align="center" style="display: flex; justify-content: center; margin-top: 10px; flex-wrap: wrap; gap: 5px;">
|
| 34 |
+
<a href="https://huggingface.co/nvidia/audio-flamingo-3">
|
| 35 |
+
<img src="https://img.shields.io/badge/🤗-Checkpoints-ED5A22.svg">
|
| 36 |
+
</a>
|
| 37 |
+
<a href="https://huggingface.co/nvidia/audio-flamingo-3-chat">
|
| 38 |
+
<img src="https://img.shields.io/badge/🤗-Checkpoints (Chat)-ED5A22.svg">
|
| 39 |
+
</a>
|
| 40 |
+
<a href="https://huggingface.co/datasets/nvidia/AudioSkills">
|
| 41 |
+
<img src="https://img.shields.io/badge/🤗-Dataset: AudioSkills--XL-ED5A22.svg">
|
| 42 |
+
</a>
|
| 43 |
+
<a href="https://huggingface.co/datasets/nvidia/LongAudio">
|
| 44 |
+
<img src="https://img.shields.io/badge/🤗-Dataset: LongAudio--XL-ED5A22.svg">
|
| 45 |
+
</a>
|
| 46 |
+
<a href="https://huggingface.co/datasets/nvidia/AF-Chat">
|
| 47 |
+
<img src="https://img.shields.io/badge/🤗-Dataset: AF--Chat-ED5A22.svg">
|
| 48 |
+
</a>
|
| 49 |
+
<a href="https://huggingface.co/datasets/nvidia/AF-Think">
|
| 50 |
+
<img src="https://img.shields.io/badge/🤗-Dataset: AF--Think-ED5A22.svg">
|
| 51 |
+
</a>
|
| 52 |
+
</div>
|
| 53 |
+
|
| 54 |
+
<div align="center" style="display: flex; justify-content: center; margin-top: 10px;">
|
| 55 |
+
<a href="https://huggingface.co/spaces/nvidia/audio_flamingo_3"><img src="https://img.shields.io/badge/🤗-Gradio Demo (7B)-5F9EA0.svg" style="margin-right: 5px;"></a>
|
| 56 |
+
</div>
|
| 57 |
## Description:
|
| 58 |
Audio Flamingo 3 (AF3) is a fully open, state-of-the-art Large Audio-Language Model (LALM) that advances reasoning and understanding across speech, sounds, and music. AF3 builds on previous work with innovations in:
|
| 59 |
|