Update README.md
Browse files
README.md
CHANGED
|
@@ -70,6 +70,8 @@ The model supports long-form audio inputs of up to 300 seconds (5 minutes) and i
|
|
| 70 |
|
| 71 |
<img src="radar_asr.png" alt="model_capability" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 72 |
|
|
|
|
|
|
|
| 73 |
We benchmark MERaLiON-2 series models with extended [AudioBench benchmark](https://github.com/AudioLLMs/AudioBench) | [LeaderBoard](https://huggingface.co/spaces/MERaLiON/AudioBench-Leaderboard) against several recently released open-source multimodal models — SALMONN-7B, Qwen2.5-Omni series and Phi-4-Multimodal — as well as two cascade model. The MERaLiON-2 series models shows stronger performance on a wide range of audio/speech understanding tasks.
|
| 74 |
|
| 75 |
|
|
|
|
| 70 |
|
| 71 |
<img src="radar_asr.png" alt="model_capability" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 72 |
|
| 73 |
+
<img src="radar_task.png" alt="model_capability" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
| 74 |
+
|
| 75 |
We benchmark MERaLiON-2 series models with extended [AudioBench benchmark](https://github.com/AudioLLMs/AudioBench) | [LeaderBoard](https://huggingface.co/spaces/MERaLiON/AudioBench-Leaderboard) against several recently released open-source multimodal models — SALMONN-7B, Qwen2.5-Omni series and Phi-4-Multimodal — as well as two cascade model. The MERaLiON-2 series models shows stronger performance on a wide range of audio/speech understanding tasks.
|
| 76 |
|
| 77 |
|