chukewang
commited on
Commit
·
e45cb1f
1
Parent(s):
574bfcc
Init
Browse files
README.md
CHANGED
|
@@ -37,7 +37,7 @@ TimeAudio is based on the fundamental architecture of SALMONN. Specifically, Tim
|
|
| 37 |
|
| 38 |
Compared with traditional speech and audio processing tasks such as speech recognition and audio caption, Example of failed cases by Qwen2-Audio and Qwen2-Audio-R1 on fine-grained tasks that require both semantics and timestamps as output.
|
| 39 |
|
| 40 |
-
<div align=center><img src="img/case.png" height="100%" width="
|
| 41 |
|
| 42 |
## How to inference in CLI
|
| 43 |
|
|
|
|
| 37 |
|
| 38 |
Compared with traditional speech and audio processing tasks such as speech recognition and audio caption, Example of failed cases by Qwen2-Audio and Qwen2-Audio-R1 on fine-grained tasks that require both semantics and timestamps as output.
|
| 39 |
|
| 40 |
+
<div align=center><img src="img/case.png" height="100%" width="70%"/></div>
|
| 41 |
|
| 42 |
## How to inference in CLI
|
| 43 |
|