Safetensors
Jayjay55 commited on
Commit
3abf43d
·
verified ·
1 Parent(s): 329dee0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -3
README.md CHANGED
@@ -12,10 +12,10 @@ license: apache-2.0
12
  </p>
13
  <p>
14
  </p>
15
- <a href="#"><img src="https://img.shields.io/badge/Paper-ArXiv-red" alt="technical report"></a>
16
- <a href="https://fireredteam.github.io/demos/fireredaudio/"><img src="https://img.shields.io/badge/Demo-Page-lightgrey" alt="version"></a>
17
  <a href="https://huggingface.co/FireRedTeam/FireRedAudio"><img src="https://img.shields.io/badge/Hugging%20Face-Model%20Page-yellow" alt="HF-model"></a>
18
- <a href="https://www.modelscope.cn/models/FireRedTeam/FireRedAudio"><img src="https://img.shields.io/badge/ModelScope-Model%20Page-624AFF?logo=modelscope&logoColor=white" alt="ModelScope-model"></a>
19
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache-2.0"></a>
20
  </div>
21
 
@@ -40,6 +40,26 @@ license: apache-2.0
40
  * ⏱️ **Go from minutes to hour-long recordings** — Understand recordings up to one hour with precise time-to-content alignment. Organize audio into timestamped structures, produce grounded summaries, retrieve content by time (or time by content), and reason over evidence distributed across the recording.
41
 
42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  ## News
44
 
45
  - [2026.08.21] We release the **FireRedAudio** code and model.
 
12
  </p>
13
  <p>
14
  </p>
15
+ <a href="https://arxiv.org/abs/2608.24168"><img src="https://img.shields.io/badge/Paper-ArXiv-red" alt="technical report"></a>
16
+ <a href="https://fireredteam.github.io/demos/fireredaudio/"><img src="https://img.shields.io/badge/Demo-Page-9B6A6A&logoColor=white&labelColor=664646" alt="FireRedAudio Demo Page"></a>
17
  <a href="https://huggingface.co/FireRedTeam/FireRedAudio"><img src="https://img.shields.io/badge/Hugging%20Face-Model%20Page-yellow" alt="HF-model"></a>
18
+ <a href="https://www.modelscope.cn/models/FireRedTeam/FireRedAudio"><img src="https://img.shields.io/badge/ModelScope-Model%20Page-624AFF&logoColor=white" alt="ModelScope-model"></a>
19
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="Apache-2.0"></a>
20
  </div>
21
 
 
40
  * ⏱️ **Go from minutes to hour-long recordings** — Understand recordings up to one hour with precise time-to-content alignment. Organize audio into timestamped structures, produce grounded summaries, retrieve content by time (or time by content), and reason over evidence distributed across the recording.
41
 
42
 
43
+ ## Long-Audio Understanding: Time–Content Alignment Demo
44
+
45
+ <table>
46
+ <tbody>
47
+ <tr>
48
+ <tr>
49
+ <th style="width: 50%; text-align: center;">English</th>
50
+ <th style="width: 50%; text-align: center;">Chinese</th>
51
+ </tr>
52
+ <td width="50%">
53
+ <video src="https://github.com/user-attachments/assets/acd36345-71e5-4c46-b828-6d4577bc24bd" controls width="100%"></video>
54
+ </td>
55
+ <td width="50%">
56
+ <video src="https://github.com/user-attachments/assets/b592e6ce-d9c5-4742-86ec-488c8f496ccc" controls width="100%"></video>
57
+ </td>
58
+ </tr>
59
+ </tbody>
60
+ </table>
61
+
62
+
63
  ## News
64
 
65
  - [2026.08.21] We release the **FireRedAudio** code and model.