Transformers
meralion
meralion-2
YingxuHe commited on
Commit
87c4b8e
·
verified ·
1 Parent(s): 32a4bb9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
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