Upload organize_model_results.json with huggingface_hub
Browse files- organize_model_results.json +2046 -0
organize_model_results.json
ADDED
@@ -0,0 +1,2046 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"ukusnews_short_test": {
|
3 |
+
"wer": {
|
4 |
+
"whisper_large_v3": 0.06168908700151238,
|
5 |
+
"Qwen-Audio-Chat": 0.10399586086125925,
|
6 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.06877338215394412,
|
7 |
+
"WavLLM_fairseq": 0.2066783411605508,
|
8 |
+
"Qwen2-Audio-7B-Instruct": 0.1194380323171217,
|
9 |
+
"SALMONN_7B": 0.09042426172092653,
|
10 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.10144869855926132,
|
11 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.0700867627159118
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"imda_part6_30s_asr_test": {
|
15 |
+
"wer": {
|
16 |
+
"whisper_large_v3": 0.1698509342851144,
|
17 |
+
"Qwen-Audio-Chat": 0.31394240863063033,
|
18 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1789273082575623,
|
19 |
+
"WavLLM_fairseq": 0.42541061709652933,
|
20 |
+
"Qwen2-Audio-7B-Instruct": 0.2245352799625317,
|
21 |
+
"SALMONN_7B": 0.24872817713464365,
|
22 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.11292172031202054,
|
23 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.17467982364056267
|
24 |
+
}
|
25 |
+
},
|
26 |
+
"covost2_en_id_test": {
|
27 |
+
"bleu": {
|
28 |
+
"whisper_large_v3": 1.600581653970121,
|
29 |
+
"Qwen-Audio-Chat": 4.102230932924371,
|
30 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 27.620150160643625,
|
31 |
+
"WavLLM_fairseq": 13.841886973016162,
|
32 |
+
"Qwen2-Audio-7B-Instruct": 16.325186897428104,
|
33 |
+
"SALMONN_7B": 14.102682915273142,
|
34 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 37.60224687716629,
|
35 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 10.930203684508578
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"imda_part3_30s_asr_test": {
|
39 |
+
"wer": {
|
40 |
+
"whisper_large_v3": 0.27026366524560785,
|
41 |
+
"Qwen-Audio-Chat": 0.6412550574306894,
|
42 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.3035544573275043,
|
43 |
+
"WavLLM_fairseq": 0.7540934640345399,
|
44 |
+
"Qwen2-Audio-7B-Instruct": 0.35076166942732234,
|
45 |
+
"SALMONN_7B": 0.6569229098215983,
|
46 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.2919053954978684,
|
47 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.29992939962527493
|
48 |
+
}
|
49 |
+
},
|
50 |
+
"gigaspeech_test": {
|
51 |
+
"wer": {
|
52 |
+
"whisper_large_v3": 0.09459022434812692,
|
53 |
+
"Qwen-Audio-Chat": 0.13018910022587737,
|
54 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.09948381629977261,
|
55 |
+
"WavLLM_fairseq": 0.15491778414546403,
|
56 |
+
"Qwen2-Audio-7B-Instruct": 0.11723812890302816,
|
57 |
+
"SALMONN_7B": 0.10765150204693537,
|
58 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.14457154747310655,
|
59 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.09515429104337297
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"covost2_ta_en_test": {
|
63 |
+
"bleu": {
|
64 |
+
"whisper_large_v3": 2.451098639578599,
|
65 |
+
"Qwen-Audio-Chat": 0.01699144301093184,
|
66 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 2.8327095799289337,
|
67 |
+
"WavLLM_fairseq": 0.1695522548322915,
|
68 |
+
"Qwen2-Audio-7B-Instruct": 0.04425838146050298,
|
69 |
+
"SALMONN_7B": 0.3649023706010388,
|
70 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 5.023057608950299,
|
71 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 2.4245628096245917
|
72 |
+
}
|
73 |
+
},
|
74 |
+
"librispeech_test_other": {
|
75 |
+
"wer": {
|
76 |
+
"whisper_large_v3": 0.03660128246354058,
|
77 |
+
"Qwen-Audio-Chat": 0.043467569561352074,
|
78 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.05307658841999735,
|
79 |
+
"WavLLM_fairseq": 0.04798834811886432,
|
80 |
+
"Qwen2-Audio-7B-Instruct": 0.060415760304159495,
|
81 |
+
"SALMONN_7B": 0.09671439650443565,
|
82 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.041576030415949455,
|
83 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.03714982881570734
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"parliament_test": {
|
87 |
+
"wer": {
|
88 |
+
"whisper_large_v3": 0.0753619074652285,
|
89 |
+
"Qwen-Audio-Chat": 0.26279685873781816,
|
90 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.06282524363705176,
|
91 |
+
"WavLLM_fairseq": 0.5216434856656259,
|
92 |
+
"Qwen2-Audio-7B-Instruct": 0.23270886555019396,
|
93 |
+
"SALMONN_7B": 0.3010928186204939,
|
94 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.058922319992430694,
|
95 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.07517267480367111
|
96 |
+
}
|
97 |
+
},
|
98 |
+
"earnings22_test": {
|
99 |
+
"wer": {
|
100 |
+
"whisper_large_v3": 0.15887899737116104,
|
101 |
+
"Qwen-Audio-Chat": 0.3664994875132684,
|
102 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1448629161356777,
|
103 |
+
"WavLLM_fairseq": 0.6671766188447099,
|
104 |
+
"Qwen2-Audio-7B-Instruct": 0.23542555661330924,
|
105 |
+
"SALMONN_7B": 0.3597423676988383,
|
106 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.1652245056860175,
|
107 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.15611126487402763
|
108 |
+
}
|
109 |
+
},
|
110 |
+
"imda_part2_asr_test": {
|
111 |
+
"wer": {
|
112 |
+
"whisper_large_v3": 0.3171008846684522,
|
113 |
+
"Qwen-Audio-Chat": 0.45479263046830615,
|
114 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.32988393799204613,
|
115 |
+
"WavLLM_fairseq": 0.4463923382842302,
|
116 |
+
"Qwen2-Audio-7B-Instruct": 0.1905689473257041,
|
117 |
+
"SALMONN_7B": 0.42346400454508565,
|
118 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.048088629169710254,
|
119 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.31912994075156237
|
120 |
+
}
|
121 |
+
},
|
122 |
+
"ukusnews_test": {
|
123 |
+
"wer": {
|
124 |
+
"whisper_large_v3": 0.07135564378899603,
|
125 |
+
"Qwen-Audio-Chat": 0.3158631121194933,
|
126 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07388920400831915,
|
127 |
+
"WavLLM_fairseq": 0.5911892607298166,
|
128 |
+
"Qwen2-Audio-7B-Instruct": 0.13843826810361126,
|
129 |
+
"SALMONN_7B": 0.18918510115333712,
|
130 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.12554358101720553,
|
131 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.07642276422764227
|
132 |
+
}
|
133 |
+
},
|
134 |
+
"earnings21_test": {
|
135 |
+
"wer": {
|
136 |
+
"whisper_large_v3": 0.11863959266711877,
|
137 |
+
"Qwen-Audio-Chat": 0.2655529121410546,
|
138 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.11416493424197618,
|
139 |
+
"WavLLM_fairseq": 0.6447482518259942,
|
140 |
+
"Qwen2-Audio-7B-Instruct": 0.18872219319407232,
|
141 |
+
"SALMONN_7B": 0.2577708974886327,
|
142 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13488732754499672,
|
143 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.11773910240019567
|
144 |
+
}
|
145 |
+
},
|
146 |
+
"covost2_zh_en_test": {
|
147 |
+
"bleu": {
|
148 |
+
"whisper_large_v3": 14.673689493155793,
|
149 |
+
"Qwen-Audio-Chat": 9.898238298955656,
|
150 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 15.209998552437538,
|
151 |
+
"WavLLM_fairseq": 2.368659001743569,
|
152 |
+
"Qwen2-Audio-7B-Instruct": 16.466557744958333,
|
153 |
+
"SALMONN_7B": 5.296039450108202,
|
154 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 18.76473995941838,
|
155 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 14.154700735606419
|
156 |
+
}
|
157 |
+
},
|
158 |
+
"covost2_en_ta_test": {
|
159 |
+
"bleu": {
|
160 |
+
"whisper_large_v3": 0.02107778621423822,
|
161 |
+
"Qwen-Audio-Chat": 0.03451483807236294,
|
162 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 8.433062902024755,
|
163 |
+
"WavLLM_fairseq": 0.0033159224040994286,
|
164 |
+
"Qwen2-Audio-7B-Instruct": 0.03245972071872916,
|
165 |
+
"SALMONN_7B": 0.00046745670226766583,
|
166 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 14.407399367512914,
|
167 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 1.0368044741318085
|
168 |
+
}
|
169 |
+
},
|
170 |
+
"librispeech_test_clean": {
|
171 |
+
"wer": {
|
172 |
+
"whisper_large_v3": 0.01878749009695552,
|
173 |
+
"Qwen-Audio-Chat": 0.020258799562379748,
|
174 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.032349945297468596,
|
175 |
+
"WavLLM_fairseq": 0.02103218017882069,
|
176 |
+
"Qwen2-Audio-7B-Instruct": 0.035141660693401744,
|
177 |
+
"SALMONN_7B": 0.10270871845172973,
|
178 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.022918474365262006,
|
179 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.018334779492209605
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"tedlium3_test": {
|
183 |
+
"wer": {
|
184 |
+
"whisper_large_v3": 0.037649480146197796,
|
185 |
+
"Qwen-Audio-Chat": 0.04052375714133636,
|
186 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.04900464852205386,
|
187 |
+
"WavLLM_fairseq": 0.06621482559171073,
|
188 |
+
"Qwen2-Audio-7B-Instruct": 0.06114048472375004,
|
189 |
+
"SALMONN_7B": 0.0459884319222171,
|
190 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.07884745040985061,
|
191 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.038146268762641496
|
192 |
+
}
|
193 |
+
},
|
194 |
+
"imda_part1_asr_test": {
|
195 |
+
"wer": {
|
196 |
+
"whisper_large_v3": 0.06844171360300393,
|
197 |
+
"Qwen-Audio-Chat": 0.10550313315290274,
|
198 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07041669714480775,
|
199 |
+
"WavLLM_fairseq": 0.10077292565771828,
|
200 |
+
"Qwen2-Audio-7B-Instruct": 0.07197717796796138,
|
201 |
+
"SALMONN_7B": 0.0925804013361617,
|
202 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.042254894789457,
|
203 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.06922195401458074
|
204 |
+
}
|
205 |
+
},
|
206 |
+
"common_voice_15_en_test": {
|
207 |
+
"wer": {
|
208 |
+
"whisper_large_v3": 0.10001863741235596,
|
209 |
+
"Qwen-Audio-Chat": 0.11272421128398918,
|
210 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.10600831614192711,
|
211 |
+
"WavLLM_fairseq": 0.14533325621300636,
|
212 |
+
"Qwen2-Audio-7B-Instruct": 0.11438872500819404,
|
213 |
+
"SALMONN_7B": 0.3062255383962828,
|
214 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.07811646454714301,
|
215 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.09876543209876543
|
216 |
+
}
|
217 |
+
},
|
218 |
+
"mediacorp_test": {
|
219 |
+
"wer": {
|
220 |
+
"whisper_large_v3": 0.12054884024828487,
|
221 |
+
"Qwen-Audio-Chat": 0.4498529892192094,
|
222 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.12455080039202875,
|
223 |
+
"WavLLM_fairseq": 0.3595230316889905,
|
224 |
+
"Qwen2-Audio-7B-Instruct": 0.18694870957203527,
|
225 |
+
"SALMONN_7B": 0.32089186540346293,
|
226 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.170859196341065,
|
227 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.13598497223129696
|
228 |
+
}
|
229 |
+
},
|
230 |
+
"idpc_short_test": {
|
231 |
+
"wer": {
|
232 |
+
"whisper_large_v3": 0.1662526275558953,
|
233 |
+
"Qwen-Audio-Chat": 0.6008025988916491,
|
234 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.16931014714313014,
|
235 |
+
"WavLLM_fairseq": 0.36728454041658704,
|
236 |
+
"Qwen2-Audio-7B-Instruct": 0.21326199120963119,
|
237 |
+
"SALMONN_7B": 0.26313777947639977,
|
238 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.24918784635964075,
|
239 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.15803554366520162
|
240 |
+
}
|
241 |
+
},
|
242 |
+
"seame_dev_man": {
|
243 |
+
"wer": {
|
244 |
+
"whisper_large_v3": 0.7225930420711975,
|
245 |
+
"Qwen-Audio-Chat": 0.8783373786407767,
|
246 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.7824973031283711,
|
247 |
+
"WavLLM_fairseq": 1.2913969795037756,
|
248 |
+
"Qwen2-Audio-7B-Instruct": 0.5522518878101402,
|
249 |
+
"SALMONN_7B": 1.2721817691477886,
|
250 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.388282092772384,
|
251 |
+
"gemini-1.5-flash": 0.9690871089536138,
|
252 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.6848705501618123
|
253 |
+
}
|
254 |
+
},
|
255 |
+
"cna_test": {
|
256 |
+
"wer": {
|
257 |
+
"whisper_large_v3": 0.13841717398269784,
|
258 |
+
"Qwen-Audio-Chat": 0.19753284203780838,
|
259 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.15171419416853574,
|
260 |
+
"WavLLM_fairseq": 0.26946491509131687,
|
261 |
+
"Qwen2-Audio-7B-Instruct": 0.2067713339741536,
|
262 |
+
"SALMONN_7B": 0.15395706504325538,
|
263 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.15924383210509452,
|
264 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.13798996048275125
|
265 |
+
}
|
266 |
+
},
|
267 |
+
"ytb_asr_batch1": {
|
268 |
+
"wer": {
|
269 |
+
"whisper_large_v3": 0.12226319428439733,
|
270 |
+
"Qwen-Audio-Chat": 0.2297764461857571,
|
271 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1400092187139894,
|
272 |
+
"WavLLM_fairseq": 0.41876008296842593,
|
273 |
+
"Qwen2-Audio-7B-Instruct": 0.16843358684796805,
|
274 |
+
"SALMONN_7B": 0.21487285856956287,
|
275 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.11484981178458939,
|
276 |
+
"gemini-1.5-flash": 0.1089344703080587,
|
277 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.12579703464700007
|
278 |
+
}
|
279 |
+
},
|
280 |
+
"mediacorp_short_test": {
|
281 |
+
"wer": {
|
282 |
+
"whisper_large_v3": 0.11715763436024286,
|
283 |
+
"Qwen-Audio-Chat": 0.2548909377108163,
|
284 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.14571621317742298,
|
285 |
+
"WavLLM_fairseq": 0.2621992354396222,
|
286 |
+
"Qwen2-Audio-7B-Instruct": 0.17180121430177647,
|
287 |
+
"SALMONN_7B": 0.1751742747919946,
|
288 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13301101866426804,
|
289 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.11434675061839443
|
290 |
+
}
|
291 |
+
},
|
292 |
+
"peoples_speech_test": {
|
293 |
+
"wer": {
|
294 |
+
"whisper_large_v3": 0.14602420615337386,
|
295 |
+
"Qwen-Audio-Chat": 0.31419144746723354,
|
296 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.20140159998943682,
|
297 |
+
"WavLLM_fairseq": 0.3792176325635977,
|
298 |
+
"Qwen2-Audio-7B-Instruct": 0.2165498391593041,
|
299 |
+
"SALMONN_7B": 0.23699946689025367,
|
300 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.21050407754683692,
|
301 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.14540692118393275
|
302 |
+
}
|
303 |
+
},
|
304 |
+
"covost2_en_zh_test": {
|
305 |
+
"bleu": {
|
306 |
+
"whisper_large_v3": 0.16408986541757878,
|
307 |
+
"Qwen-Audio-Chat": 15.330641138043728,
|
308 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 35.274306071307024,
|
309 |
+
"WavLLM_fairseq": 31.96381187282953,
|
310 |
+
"Qwen2-Audio-7B-Instruct": 25.765420247070075,
|
311 |
+
"SALMONN_7B": 33.88941292215531,
|
312 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 43.941098854450516,
|
313 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 5.987143868370054
|
314 |
+
}
|
315 |
+
},
|
316 |
+
"tedlium3_long_form_test": {
|
317 |
+
"wer": {
|
318 |
+
"whisper_large_v3": 0.03208650948413402,
|
319 |
+
"Qwen-Audio-Chat": 0.2911540507002305,
|
320 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.04396383619925545,
|
321 |
+
"WavLLM_fairseq": 0.4536784258110264,
|
322 |
+
"Qwen2-Audio-7B-Instruct": 0.08739585179932637,
|
323 |
+
"SALMONN_7B": 0.14231519234178336,
|
324 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.10228682857649353,
|
325 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.04754476156709803
|
326 |
+
}
|
327 |
+
},
|
328 |
+
"seame_dev_sge": {
|
329 |
+
"wer": {
|
330 |
+
"whisper_large_v3": 0.5377268970583734,
|
331 |
+
"Qwen-Audio-Chat": 1.05567969634822,
|
332 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.5840399155162387,
|
333 |
+
"WavLLM_fairseq": 1.2204842511249197,
|
334 |
+
"Qwen2-Audio-7B-Instruct": 0.5486546879304539,
|
335 |
+
"SALMONN_7B": 1.0189782362484312,
|
336 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.35550521901496834,
|
337 |
+
"gemini-1.5-flash": 1.1100431601824359,
|
338 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.507882090054792
|
339 |
+
}
|
340 |
+
},
|
341 |
+
"aishell_asr_zh_test": {
|
342 |
+
"wer": {
|
343 |
+
"whisper_large_v3": 0.12359684029221357,
|
344 |
+
"Qwen-Audio-Chat": 0.9469917443725129,
|
345 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.20886539565639167,
|
346 |
+
"WavLLM_fairseq": 0.7054601967888183,
|
347 |
+
"Qwen2-Audio-7B-Instruct": 0.09260359129694522,
|
348 |
+
"SALMONN_7B": 0.8259290055631446,
|
349 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13165449110094832,
|
350 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.12450753301261111
|
351 |
+
}
|
352 |
+
},
|
353 |
+
"covost2_id_en_test": {
|
354 |
+
"bleu": {
|
355 |
+
"whisper_large_v3": 46.01512198258627,
|
356 |
+
"Qwen-Audio-Chat": 0.45648619714728844,
|
357 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 46.80524126004861,
|
358 |
+
"WavLLM_fairseq": 5.933522277713613,
|
359 |
+
"Qwen2-Audio-7B-Instruct": 6.326113431899141,
|
360 |
+
"SALMONN_7B": 26.89649039333571,
|
361 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 44.43289180618449,
|
362 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 46.79924664837527
|
363 |
+
}
|
364 |
+
},
|
365 |
+
"ytb_asr_batch2": {
|
366 |
+
"wer": {
|
367 |
+
"whisper_large_v3": 0.17210509244242622,
|
368 |
+
"Qwen-Audio-Chat": 0.4315277327278625,
|
369 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.2192622950819672,
|
370 |
+
"WavLLM_fairseq": 0.48091685587631094,
|
371 |
+
"Qwen2-Audio-7B-Instruct": 0.2080008649583739,
|
372 |
+
"SALMONN_7B": 0.3238620391393664,
|
373 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.15162720294085846,
|
374 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.23561466104443723
|
375 |
+
}
|
376 |
+
},
|
377 |
+
"imda_part5_30s_asr_test": {
|
378 |
+
"wer": {
|
379 |
+
"whisper_large_v3": 0.2143555471246589,
|
380 |
+
"Qwen-Audio-Chat": 0.3016882870525747,
|
381 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.22881615619208825,
|
382 |
+
"WavLLM_fairseq": 0.39796588405247263,
|
383 |
+
"Qwen2-Audio-7B-Instruct": 0.27856006770658537,
|
384 |
+
"SALMONN_7B": 0.34868891450584405,
|
385 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.17694182194919086,
|
386 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.22004640235805695
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"parliament_short_test": {
|
390 |
+
"wer": {
|
391 |
+
"whisper_large_v3": 0.05543951935226013,
|
392 |
+
"Qwen-Audio-Chat": 0.09347360821020603,
|
393 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07325752301384698,
|
394 |
+
"WavLLM_fairseq": 0.09512390087929656,
|
395 |
+
"Qwen2-Audio-7B-Instruct": 0.08416492612361723,
|
396 |
+
"SALMONN_7B": 0.08676929424202573,
|
397 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.056935097083623425,
|
398 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.05742502771975968
|
399 |
+
}
|
400 |
+
},
|
401 |
+
"idpc_test": {
|
402 |
+
"wer": {
|
403 |
+
"whisper_large_v3": 0.19880239520958085,
|
404 |
+
"Qwen-Audio-Chat": 0.7710863986313088,
|
405 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.16766467065868262,
|
406 |
+
"WavLLM_fairseq": 0.7686911890504705,
|
407 |
+
"Qwen2-Audio-7B-Instruct": 0.19093242087254064,
|
408 |
+
"SALMONN_7B": 0.4550898203592814,
|
409 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.30008554319931563,
|
410 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.17741659538066723
|
411 |
+
}
|
412 |
+
},
|
413 |
+
"imda_part3_30s_ds_human_test": {
|
414 |
+
"llama3_70b_judge": {
|
415 |
+
"Qwen-Audio-Chat": {
|
416 |
+
"judge_score": 16.4,
|
417 |
+
"success_rate": 1.0
|
418 |
+
},
|
419 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
420 |
+
"judge_score": 45.4,
|
421 |
+
"success_rate": 1.0
|
422 |
+
},
|
423 |
+
"WavLLM_fairseq": {
|
424 |
+
"judge_score": 31.6,
|
425 |
+
"success_rate": 1.0
|
426 |
+
},
|
427 |
+
"Qwen2-Audio-7B-Instruct": {
|
428 |
+
"judge_score": 33.8,
|
429 |
+
"success_rate": 1.0
|
430 |
+
},
|
431 |
+
"SALMONN_7B": {
|
432 |
+
"judge_score": 9.0,
|
433 |
+
"success_rate": 0.99
|
434 |
+
},
|
435 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
436 |
+
"judge_score": 48.4,
|
437 |
+
"success_rate": 0.99
|
438 |
+
},
|
439 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
440 |
+
"judge_score": 37.400000000000006,
|
441 |
+
"success_rate": 1.0
|
442 |
+
}
|
443 |
+
},
|
444 |
+
"gpt4o_judge": {
|
445 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
446 |
+
"judge_score": 47.400000000000006,
|
447 |
+
"success_rate": 1.0
|
448 |
+
}
|
449 |
+
}
|
450 |
+
},
|
451 |
+
"cn_college_listen_mcq_test": {
|
452 |
+
"llama3_70b_judge": {
|
453 |
+
"Qwen-Audio-Chat": {
|
454 |
+
"judge_score": 63.232056362835756,
|
455 |
+
"success_rate": 0.9995596653456627
|
456 |
+
},
|
457 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
458 |
+
"judge_score": 91.85380889476001,
|
459 |
+
"success_rate": 1.0
|
460 |
+
},
|
461 |
+
"WavLLM_fairseq": {
|
462 |
+
"judge_score": 66.31439894319684,
|
463 |
+
"success_rate": 1.0
|
464 |
+
},
|
465 |
+
"Qwen2-Audio-7B-Instruct": {
|
466 |
+
"judge_score": 74.7247908410392,
|
467 |
+
"success_rate": 0.9995596653456627
|
468 |
+
},
|
469 |
+
"SALMONN_7B": {
|
470 |
+
"judge_score": 50.99075297225891,
|
471 |
+
"success_rate": 1.0
|
472 |
+
},
|
473 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
474 |
+
"judge_score": 88.50726552179657,
|
475 |
+
"success_rate": 1.0
|
476 |
+
},
|
477 |
+
"gemini-1.5-flash": {
|
478 |
+
"judge_score": 89.25583443416997,
|
479 |
+
"success_rate": 0.9991193306913254
|
480 |
+
},
|
481 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
482 |
+
"judge_score": 85.2928225451343,
|
483 |
+
"success_rate": 1.0
|
484 |
+
}
|
485 |
+
}
|
486 |
+
},
|
487 |
+
"imda_part3_30s_sqa_test": {
|
488 |
+
"llama3_70b_judge": {
|
489 |
+
"Qwen-Audio-Chat": {
|
490 |
+
"judge_score": 51.08,
|
491 |
+
"success_rate": 0.998
|
492 |
+
},
|
493 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
494 |
+
"judge_score": 70.17999999999999,
|
495 |
+
"success_rate": 1.0
|
496 |
+
},
|
497 |
+
"Qwen2-Audio-7B-Instruct": {
|
498 |
+
"judge_score": 60.620000000000005,
|
499 |
+
"success_rate": 1.0
|
500 |
+
},
|
501 |
+
"SALMONN_7B": {
|
502 |
+
"judge_score": 50.8,
|
503 |
+
"success_rate": 0.999
|
504 |
+
},
|
505 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
506 |
+
"judge_score": 70.28,
|
507 |
+
"success_rate": 1.0
|
508 |
+
}
|
509 |
+
},
|
510 |
+
"gpt4o_judge": {
|
511 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
512 |
+
"judge_score": 73.0,
|
513 |
+
"success_rate": 0.999
|
514 |
+
}
|
515 |
+
}
|
516 |
+
},
|
517 |
+
"openhermes_audio_test": {
|
518 |
+
"llama3_70b_judge": {
|
519 |
+
"Qwen-Audio-Chat": {
|
520 |
+
"judge_score": 10.600000000000001,
|
521 |
+
"success_rate": 1.0
|
522 |
+
},
|
523 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
524 |
+
"judge_score": 72.2,
|
525 |
+
"success_rate": 0.96
|
526 |
+
},
|
527 |
+
"WavLLM_fairseq": {
|
528 |
+
"judge_score": 19.2,
|
529 |
+
"success_rate": 1.0
|
530 |
+
},
|
531 |
+
"Qwen2-Audio-7B-Instruct": {
|
532 |
+
"judge_score": 44.800000000000004,
|
533 |
+
"success_rate": 0.96
|
534 |
+
},
|
535 |
+
"SALMONN_7B": {
|
536 |
+
"judge_score": 15.8,
|
537 |
+
"success_rate": 1.0
|
538 |
+
},
|
539 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
540 |
+
"judge_score": 65.6,
|
541 |
+
"success_rate": 1.0
|
542 |
+
},
|
543 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
544 |
+
"judge_score": 63.0,
|
545 |
+
"success_rate": 0.93
|
546 |
+
}
|
547 |
+
},
|
548 |
+
"gpt4o_judge": {
|
549 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
550 |
+
"judge_score": 75.0,
|
551 |
+
"success_rate": 1.0
|
552 |
+
}
|
553 |
+
}
|
554 |
+
},
|
555 |
+
"imda_part5_30s_sqa_human_test": {
|
556 |
+
"llama3_70b_judge": {
|
557 |
+
"Qwen-Audio-Chat": {
|
558 |
+
"judge_score": 47.800000000000004,
|
559 |
+
"success_rate": 1.0
|
560 |
+
},
|
561 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
562 |
+
"judge_score": 74.0,
|
563 |
+
"success_rate": 1.0
|
564 |
+
},
|
565 |
+
"WavLLM_fairseq": {
|
566 |
+
"judge_score": 50.8,
|
567 |
+
"success_rate": 0.99
|
568 |
+
},
|
569 |
+
"Qwen2-Audio-7B-Instruct": {
|
570 |
+
"judge_score": 51.6,
|
571 |
+
"success_rate": 1.0
|
572 |
+
},
|
573 |
+
"SALMONN_7B": {
|
574 |
+
"judge_score": 44.6,
|
575 |
+
"success_rate": 1.0
|
576 |
+
},
|
577 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
578 |
+
"judge_score": 64.80000000000001,
|
579 |
+
"success_rate": 1.0
|
580 |
+
},
|
581 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
582 |
+
"judge_score": 57.800000000000004,
|
583 |
+
"success_rate": 1.0
|
584 |
+
}
|
585 |
+
},
|
586 |
+
"gpt4o_judge": {
|
587 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
588 |
+
"judge_score": 64.80000000000001,
|
589 |
+
"success_rate": 1.0
|
590 |
+
}
|
591 |
+
}
|
592 |
+
},
|
593 |
+
"slue_p2_sqa5_test": {
|
594 |
+
"llama3_70b_judge": {
|
595 |
+
"Qwen-Audio-Chat": {
|
596 |
+
"judge_score": 79.36274509803921,
|
597 |
+
"success_rate": 0.9975490196078431
|
598 |
+
},
|
599 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
600 |
+
"judge_score": 88.57843137254902,
|
601 |
+
"success_rate": 1.0
|
602 |
+
},
|
603 |
+
"WavLLM_fairseq": {
|
604 |
+
"judge_score": 83.92156862745098,
|
605 |
+
"success_rate": 1.0
|
606 |
+
},
|
607 |
+
"Qwen2-Audio-7B-Instruct": {
|
608 |
+
"judge_score": 80.04901960784315,
|
609 |
+
"success_rate": 1.0
|
610 |
+
},
|
611 |
+
"SALMONN_7B": {
|
612 |
+
"judge_score": 83.48039215686273,
|
613 |
+
"success_rate": 1.0
|
614 |
+
},
|
615 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
616 |
+
"judge_score": 86.76470588235293,
|
617 |
+
"success_rate": 1.0
|
618 |
+
},
|
619 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
620 |
+
"judge_score": 82.99019607843137,
|
621 |
+
"success_rate": 1.0
|
622 |
+
}
|
623 |
+
},
|
624 |
+
"gpt4o_judge": {
|
625 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
626 |
+
"judge_score": 87.79411764705883,
|
627 |
+
"success_rate": 1.0
|
628 |
+
}
|
629 |
+
}
|
630 |
+
},
|
631 |
+
"ytb_sds_batch1": {
|
632 |
+
"llama3_70b_judge": {
|
633 |
+
"Qwen-Audio-Chat": {
|
634 |
+
"judge_score": 43.878954607977995,
|
635 |
+
"success_rate": 0.9917469050894085
|
636 |
+
},
|
637 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
638 |
+
"judge_score": 64.12654745529574,
|
639 |
+
"success_rate": 0.9986244841815681
|
640 |
+
},
|
641 |
+
"WavLLM_fairseq": {
|
642 |
+
"judge_score": 55.625859697386524,
|
643 |
+
"success_rate": 0.9917469050894085
|
644 |
+
},
|
645 |
+
"Qwen2-Audio-7B-Instruct": {
|
646 |
+
"judge_score": 51.5818431911967,
|
647 |
+
"success_rate": 0.9986244841815681
|
648 |
+
},
|
649 |
+
"SALMONN_7B": {
|
650 |
+
"judge_score": 31.279229711141674,
|
651 |
+
"success_rate": 0.9972489683631361
|
652 |
+
},
|
653 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
654 |
+
"judge_score": 53.97524071526823,
|
655 |
+
"success_rate": 0.9944979367262724
|
656 |
+
},
|
657 |
+
"gemini-1.5-flash": {
|
658 |
+
"judge_score": 65.9697386519945,
|
659 |
+
"success_rate": 0.9931224209078404
|
660 |
+
},
|
661 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
662 |
+
"judge_score": 59.44979367262724,
|
663 |
+
"success_rate": 0.9972489683631361
|
664 |
+
}
|
665 |
+
}
|
666 |
+
},
|
667 |
+
"voxceleb_gender_test": {
|
668 |
+
"llama3_70b_judge": {
|
669 |
+
"Qwen-Audio-Chat": {
|
670 |
+
"judge_score": 70.5990972507181,
|
671 |
+
"success_rate": 0.9997948297086582
|
672 |
+
},
|
673 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
674 |
+
"judge_score": 34.94050061551087,
|
675 |
+
"success_rate": 1.0
|
676 |
+
},
|
677 |
+
"WavLLM_fairseq": {
|
678 |
+
"judge_score": 69.61427985227739,
|
679 |
+
"success_rate": 1.0
|
680 |
+
},
|
681 |
+
"Qwen2-Audio-7B-Instruct": {
|
682 |
+
"judge_score": 99.1177677472302,
|
683 |
+
"success_rate": 1.0
|
684 |
+
},
|
685 |
+
"SALMONN_7B": {
|
686 |
+
"judge_score": 88.79770209273697,
|
687 |
+
"success_rate": 1.0
|
688 |
+
},
|
689 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
690 |
+
"judge_score": 99.75379565038982,
|
691 |
+
"success_rate": 1.0
|
692 |
+
},
|
693 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
694 |
+
"judge_score": 42.921624948707425,
|
695 |
+
"success_rate": 1.0
|
696 |
+
}
|
697 |
+
}
|
698 |
+
},
|
699 |
+
"dream_tts_mcq_test": {
|
700 |
+
"llama3_70b_judge": {
|
701 |
+
"Qwen-Audio-Chat": {
|
702 |
+
"judge_score": 59.749085206481965,
|
703 |
+
"success_rate": 1.0
|
704 |
+
},
|
705 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
706 |
+
"judge_score": 89.33612127548353,
|
707 |
+
"success_rate": 1.0
|
708 |
+
},
|
709 |
+
"WavLLM_fairseq": {
|
710 |
+
"judge_score": 66.5446941975954,
|
711 |
+
"success_rate": 0.9984317825405122
|
712 |
+
},
|
713 |
+
"Qwen2-Audio-7B-Instruct": {
|
714 |
+
"judge_score": 66.49242028227914,
|
715 |
+
"success_rate": 0.9994772608468374
|
716 |
+
},
|
717 |
+
"SALMONN_7B": {
|
718 |
+
"judge_score": 56.455828541557764,
|
719 |
+
"success_rate": 1.0
|
720 |
+
},
|
721 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
722 |
+
"judge_score": 84.31782540512285,
|
723 |
+
"success_rate": 1.0
|
724 |
+
},
|
725 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
726 |
+
"judge_score": 86.4610559330894,
|
727 |
+
"success_rate": 1.0
|
728 |
+
}
|
729 |
+
}
|
730 |
+
},
|
731 |
+
"ytb_sqa_batch1": {
|
732 |
+
"llama3_70b_judge": {
|
733 |
+
"Qwen-Audio-Chat": {
|
734 |
+
"judge_score": 60.827586206896555,
|
735 |
+
"success_rate": 0.9980295566502463
|
736 |
+
},
|
737 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
738 |
+
"judge_score": 70.18719211822659,
|
739 |
+
"success_rate": 1.0
|
740 |
+
},
|
741 |
+
"WavLLM_fairseq": {
|
742 |
+
"judge_score": 60.70935960591133,
|
743 |
+
"success_rate": 1.0
|
744 |
+
},
|
745 |
+
"Qwen2-Audio-7B-Instruct": {
|
746 |
+
"judge_score": 60.453201970443345,
|
747 |
+
"success_rate": 0.9980295566502463
|
748 |
+
},
|
749 |
+
"SALMONN_7B": {
|
750 |
+
"judge_score": 55.665024630541865,
|
751 |
+
"success_rate": 0.9990147783251232
|
752 |
+
},
|
753 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
754 |
+
"judge_score": 64.51231527093596,
|
755 |
+
"success_rate": 0.9980295566502463
|
756 |
+
},
|
757 |
+
"gemini-1.5-flash": {
|
758 |
+
"judge_score": 78.06896551724138,
|
759 |
+
"success_rate": 0.9980295566502463
|
760 |
+
},
|
761 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
762 |
+
"judge_score": 67.3103448275862,
|
763 |
+
"success_rate": 1.0
|
764 |
+
}
|
765 |
+
}
|
766 |
+
},
|
767 |
+
"spoken_squad_test": {
|
768 |
+
"llama3_70b_judge": {
|
769 |
+
"Qwen-Audio-Chat": {
|
770 |
+
"judge_score": 64.8327415436367,
|
771 |
+
"success_rate": 0.9990655952158475
|
772 |
+
},
|
773 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
774 |
+
"judge_score": 88.61894972902262,
|
775 |
+
"success_rate": 0.9998131190431695
|
776 |
+
},
|
777 |
+
"WavLLM_fairseq": {
|
778 |
+
"judge_score": 77.64903756307233,
|
779 |
+
"success_rate": 0.997383666604373
|
780 |
+
},
|
781 |
+
"Qwen2-Audio-7B-Instruct": {
|
782 |
+
"judge_score": 64.86264249672958,
|
783 |
+
"success_rate": 0.9971967856475425
|
784 |
+
},
|
785 |
+
"SALMONN_7B": {
|
786 |
+
"judge_score": 66.39506634273968,
|
787 |
+
"success_rate": 0.9994393571295085
|
788 |
+
},
|
789 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
790 |
+
"judge_score": 73.66473556344609,
|
791 |
+
"success_rate": 0.999252476172678
|
792 |
+
},
|
793 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
794 |
+
"judge_score": 83.81984675761541,
|
795 |
+
"success_rate": 0.998131190431695
|
796 |
+
}
|
797 |
+
},
|
798 |
+
"gpt4o_judge": {
|
799 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
800 |
+
"judge_score": 90.12521024107643,
|
801 |
+
"success_rate": 1.0
|
802 |
+
}
|
803 |
+
}
|
804 |
+
},
|
805 |
+
"imda_part4_30s_sqa_test": {
|
806 |
+
"llama3_70b_judge": {
|
807 |
+
"Qwen-Audio-Chat": {
|
808 |
+
"judge_score": 41.92,
|
809 |
+
"success_rate": 0.999
|
810 |
+
},
|
811 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
812 |
+
"judge_score": 66.34,
|
813 |
+
"success_rate": 1.0
|
814 |
+
},
|
815 |
+
"Qwen2-Audio-7B-Instruct": {
|
816 |
+
"judge_score": 50.279999999999994,
|
817 |
+
"success_rate": 0.999
|
818 |
+
},
|
819 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
820 |
+
"judge_score": 61.980000000000004,
|
821 |
+
"success_rate": 1.0
|
822 |
+
}
|
823 |
+
},
|
824 |
+
"gpt4o_judge": {
|
825 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
826 |
+
"judge_score": 64.9,
|
827 |
+
"success_rate": 1.0
|
828 |
+
}
|
829 |
+
}
|
830 |
+
},
|
831 |
+
"imda_gr_dialogue": {
|
832 |
+
"llama3_70b_judge": {
|
833 |
+
"Qwen-Audio-Chat": {
|
834 |
+
"judge_score": 37.2,
|
835 |
+
"success_rate": 0.9996666666666667
|
836 |
+
},
|
837 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
838 |
+
"judge_score": 19.6,
|
839 |
+
"success_rate": 1.0
|
840 |
+
},
|
841 |
+
"WavLLM_fairseq": {
|
842 |
+
"judge_score": 46.766666666666666,
|
843 |
+
"success_rate": 1.0
|
844 |
+
},
|
845 |
+
"Qwen2-Audio-7B-Instruct": {
|
846 |
+
"judge_score": 61.56666666666667,
|
847 |
+
"success_rate": 0.9996666666666667
|
848 |
+
},
|
849 |
+
"SALMONN_7B": {
|
850 |
+
"judge_score": 42.733333333333334,
|
851 |
+
"success_rate": 0.9993333333333333
|
852 |
+
},
|
853 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
854 |
+
"judge_score": 93.76666666666667,
|
855 |
+
"success_rate": 1.0
|
856 |
+
},
|
857 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
858 |
+
"judge_score": 25.433333333333337,
|
859 |
+
"success_rate": 0.9996666666666667
|
860 |
+
}
|
861 |
+
}
|
862 |
+
},
|
863 |
+
"imda_ar_dialogue": {
|
864 |
+
"llama3_70b_judge": {
|
865 |
+
"Qwen-Audio-Chat": {
|
866 |
+
"judge_score": 0.6666666666666667,
|
867 |
+
"success_rate": 0.9996666666666667
|
868 |
+
},
|
869 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
870 |
+
"judge_score": 7.633333333333334,
|
871 |
+
"success_rate": 1.0
|
872 |
+
},
|
873 |
+
"WavLLM_fairseq": {
|
874 |
+
"judge_score": 0.23333333333333336,
|
875 |
+
"success_rate": 0.9996666666666667
|
876 |
+
},
|
877 |
+
"Qwen2-Audio-7B-Instruct": {
|
878 |
+
"judge_score": 0.9666666666666667,
|
879 |
+
"success_rate": 1.0
|
880 |
+
},
|
881 |
+
"SALMONN_7B": {
|
882 |
+
"judge_score": 0.06666666666666667,
|
883 |
+
"success_rate": 1.0
|
884 |
+
},
|
885 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
886 |
+
"judge_score": 77.83333333333333,
|
887 |
+
"success_rate": 1.0
|
888 |
+
},
|
889 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
890 |
+
"judge_score": 9.666666666666666,
|
891 |
+
"success_rate": 0.9986666666666667
|
892 |
+
}
|
893 |
+
}
|
894 |
+
},
|
895 |
+
"audiocaps_test": {
|
896 |
+
"meteor": {
|
897 |
+
"Qwen-Audio-Chat": 0.27553015076950976,
|
898 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.05796819723943051,
|
899 |
+
"WavLLM_fairseq": 0.041732965094428545,
|
900 |
+
"Qwen2-Audio-7B-Instruct": 0.19891712076314283,
|
901 |
+
"SALMONN_7B": 0.20994052484339956,
|
902 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.24920047034353812,
|
903 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.07953048457785493
|
904 |
+
},
|
905 |
+
"llama3_70b_judge": {
|
906 |
+
"Qwen-Audio-Chat": {
|
907 |
+
"judge_score": 47.04090909090909,
|
908 |
+
"success_rate": 0.9990909090909091
|
909 |
+
},
|
910 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
911 |
+
"judge_score": 3.0954545454545457,
|
912 |
+
"success_rate": 0.9995454545454545
|
913 |
+
},
|
914 |
+
"WavLLM_fairseq": {
|
915 |
+
"judge_score": 5.5,
|
916 |
+
"success_rate": 0.9977272727272727
|
917 |
+
},
|
918 |
+
"Qwen2-Audio-7B-Instruct": {
|
919 |
+
"judge_score": 40.77727272727273,
|
920 |
+
"success_rate": 0.9977272727272727
|
921 |
+
},
|
922 |
+
"SALMONN_7B": {
|
923 |
+
"judge_score": 37.445454545454545,
|
924 |
+
"success_rate": 0.9988636363636364
|
925 |
+
},
|
926 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
927 |
+
"judge_score": 38.00454545454545,
|
928 |
+
"success_rate": 0.9997727272727273
|
929 |
+
},
|
930 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
931 |
+
"judge_score": 2.4727272727272727,
|
932 |
+
"success_rate": 0.9997727272727273
|
933 |
+
}
|
934 |
+
},
|
935 |
+
"gpt4o_judge": {
|
936 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
937 |
+
"judge_score": 4.868181818181818,
|
938 |
+
"success_rate": 0.9981818181818182
|
939 |
+
}
|
940 |
+
}
|
941 |
+
},
|
942 |
+
"imda_part5_30s_ds_test": {
|
943 |
+
"llama3_70b_judge": {
|
944 |
+
"Qwen-Audio-Chat": {
|
945 |
+
"judge_score": 39.14,
|
946 |
+
"success_rate": 0.996
|
947 |
+
},
|
948 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
949 |
+
"judge_score": 61.48,
|
950 |
+
"success_rate": 0.996
|
951 |
+
},
|
952 |
+
"Qwen2-Audio-7B-Instruct": {
|
953 |
+
"judge_score": 45.38,
|
954 |
+
"success_rate": 0.997
|
955 |
+
},
|
956 |
+
"SALMONN_7B": {
|
957 |
+
"judge_score": 24.340000000000003,
|
958 |
+
"success_rate": 0.998
|
959 |
+
},
|
960 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
961 |
+
"judge_score": 54.379999999999995,
|
962 |
+
"success_rate": 0.998
|
963 |
+
}
|
964 |
+
},
|
965 |
+
"gpt4o_judge": {
|
966 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
967 |
+
"judge_score": 63.68000000000001,
|
968 |
+
"success_rate": 1.0
|
969 |
+
}
|
970 |
+
}
|
971 |
+
},
|
972 |
+
"ytb_pqa_batch1": {
|
973 |
+
"llama3_70b_judge": {
|
974 |
+
"Qwen-Audio-Chat": {
|
975 |
+
"judge_score": 37.16117216117216,
|
976 |
+
"success_rate": 0.9990842490842491
|
977 |
+
},
|
978 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
979 |
+
"judge_score": 55.01831501831502,
|
980 |
+
"success_rate": 0.9990842490842491
|
981 |
+
},
|
982 |
+
"WavLLM_fairseq": {
|
983 |
+
"judge_score": 40.95238095238095,
|
984 |
+
"success_rate": 1.0
|
985 |
+
},
|
986 |
+
"Qwen2-Audio-7B-Instruct": {
|
987 |
+
"judge_score": 36.97802197802198,
|
988 |
+
"success_rate": 0.9981684981684982
|
989 |
+
},
|
990 |
+
"SALMONN_7B": {
|
991 |
+
"judge_score": 32.124542124542124,
|
992 |
+
"success_rate": 1.0
|
993 |
+
},
|
994 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
995 |
+
"judge_score": 40.97069597069597,
|
996 |
+
"success_rate": 0.9990842490842491
|
997 |
+
},
|
998 |
+
"gemini-1.5-flash": {
|
999 |
+
"judge_score": 49.908424908424905,
|
1000 |
+
"success_rate": 0.9972527472527473
|
1001 |
+
},
|
1002 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1003 |
+
"judge_score": 52.252747252747255,
|
1004 |
+
"success_rate": 0.9990842490842491
|
1005 |
+
}
|
1006 |
+
}
|
1007 |
+
},
|
1008 |
+
"imda_ar_sentence": {
|
1009 |
+
"llama3_70b_judge": {
|
1010 |
+
"Qwen-Audio-Chat": {
|
1011 |
+
"judge_score": 3.933333333333333,
|
1012 |
+
"success_rate": 0.9996666666666667
|
1013 |
+
},
|
1014 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1015 |
+
"judge_score": 26.016666666666666,
|
1016 |
+
"success_rate": 0.9998333333333334
|
1017 |
+
},
|
1018 |
+
"WavLLM_fairseq": {
|
1019 |
+
"judge_score": 2.6833333333333336,
|
1020 |
+
"success_rate": 0.999
|
1021 |
+
},
|
1022 |
+
"Qwen2-Audio-7B-Instruct": {
|
1023 |
+
"judge_score": 2.55,
|
1024 |
+
"success_rate": 0.9998333333333334
|
1025 |
+
},
|
1026 |
+
"SALMONN_7B": {
|
1027 |
+
"judge_score": 2.5166666666666666,
|
1028 |
+
"success_rate": 0.999
|
1029 |
+
},
|
1030 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1031 |
+
"judge_score": 7.816666666666666,
|
1032 |
+
"success_rate": 0.9995
|
1033 |
+
},
|
1034 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1035 |
+
"judge_score": 12.416666666666666,
|
1036 |
+
"success_rate": 0.9995
|
1037 |
+
}
|
1038 |
+
}
|
1039 |
+
},
|
1040 |
+
"imda_part6_30s_sqa_human_test": {
|
1041 |
+
"llama3_70b_judge": {
|
1042 |
+
"Qwen-Audio-Chat": {
|
1043 |
+
"judge_score": 51.4,
|
1044 |
+
"success_rate": 1.0
|
1045 |
+
},
|
1046 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1047 |
+
"judge_score": 71.6,
|
1048 |
+
"success_rate": 1.0
|
1049 |
+
},
|
1050 |
+
"WavLLM_fairseq": {
|
1051 |
+
"judge_score": 62.199999999999996,
|
1052 |
+
"success_rate": 1.0
|
1053 |
+
},
|
1054 |
+
"Qwen2-Audio-7B-Instruct": {
|
1055 |
+
"judge_score": 53.6,
|
1056 |
+
"success_rate": 1.0
|
1057 |
+
},
|
1058 |
+
"SALMONN_7B": {
|
1059 |
+
"judge_score": 46.8,
|
1060 |
+
"success_rate": 1.0
|
1061 |
+
},
|
1062 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1063 |
+
"judge_score": 67.2,
|
1064 |
+
"success_rate": 1.0
|
1065 |
+
},
|
1066 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1067 |
+
"judge_score": 64.0,
|
1068 |
+
"success_rate": 1.0
|
1069 |
+
}
|
1070 |
+
},
|
1071 |
+
"gpt4o_judge": {
|
1072 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1073 |
+
"judge_score": 67.0,
|
1074 |
+
"success_rate": 1.0
|
1075 |
+
}
|
1076 |
+
}
|
1077 |
+
},
|
1078 |
+
"imda_gr_sentence": {
|
1079 |
+
"llama3_70b_judge": {
|
1080 |
+
"Qwen-Audio-Chat": {
|
1081 |
+
"judge_score": 57.550000000000004,
|
1082 |
+
"success_rate": 1.0
|
1083 |
+
},
|
1084 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1085 |
+
"judge_score": 26.35,
|
1086 |
+
"success_rate": 1.0
|
1087 |
+
},
|
1088 |
+
"WavLLM_fairseq": {
|
1089 |
+
"judge_score": 49.06666666666666,
|
1090 |
+
"success_rate": 0.9996666666666667
|
1091 |
+
},
|
1092 |
+
"Qwen2-Audio-7B-Instruct": {
|
1093 |
+
"judge_score": 68.38333333333333,
|
1094 |
+
"success_rate": 0.9996666666666667
|
1095 |
+
},
|
1096 |
+
"SALMONN_7B": {
|
1097 |
+
"judge_score": 59.766666666666666,
|
1098 |
+
"success_rate": 1.0
|
1099 |
+
},
|
1100 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1101 |
+
"judge_score": 66.13333333333333,
|
1102 |
+
"success_rate": 1.0
|
1103 |
+
},
|
1104 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1105 |
+
"judge_score": 36.016666666666666,
|
1106 |
+
"success_rate": 1.0
|
1107 |
+
}
|
1108 |
+
}
|
1109 |
+
},
|
1110 |
+
"imda_part4_30s_ds_test": {
|
1111 |
+
"llama3_70b_judge": {
|
1112 |
+
"Qwen-Audio-Chat": {
|
1113 |
+
"judge_score": 18.060000000000002,
|
1114 |
+
"success_rate": 0.994
|
1115 |
+
},
|
1116 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1117 |
+
"judge_score": 43.4,
|
1118 |
+
"success_rate": 0.999
|
1119 |
+
},
|
1120 |
+
"Qwen2-Audio-7B-Instruct": {
|
1121 |
+
"judge_score": 25.019999999999996,
|
1122 |
+
"success_rate": 0.998
|
1123 |
+
},
|
1124 |
+
"SALMONN_7B": {
|
1125 |
+
"judge_score": 9.399999999999999,
|
1126 |
+
"success_rate": 0.999
|
1127 |
+
},
|
1128 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1129 |
+
"judge_score": 37.879999999999995,
|
1130 |
+
"success_rate": 0.993
|
1131 |
+
}
|
1132 |
+
},
|
1133 |
+
"gpt4o_judge": {
|
1134 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1135 |
+
"judge_score": 47.74,
|
1136 |
+
"success_rate": 0.999
|
1137 |
+
}
|
1138 |
+
}
|
1139 |
+
},
|
1140 |
+
"meld_emotion_test": {
|
1141 |
+
"llama3_70b_judge": {
|
1142 |
+
"Qwen-Audio-Chat": {
|
1143 |
+
"judge_score": 50.72796934865901,
|
1144 |
+
"success_rate": 1.0
|
1145 |
+
},
|
1146 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1147 |
+
"judge_score": 47.356321839080465,
|
1148 |
+
"success_rate": 1.0
|
1149 |
+
},
|
1150 |
+
"WavLLM_fairseq": {
|
1151 |
+
"judge_score": 41.57088122605364,
|
1152 |
+
"success_rate": 1.0
|
1153 |
+
},
|
1154 |
+
"Qwen2-Audio-7B-Instruct": {
|
1155 |
+
"judge_score": 41.60919540229885,
|
1156 |
+
"success_rate": 1.0
|
1157 |
+
},
|
1158 |
+
"SALMONN_7B": {
|
1159 |
+
"judge_score": 30.536398467432953,
|
1160 |
+
"success_rate": 1.0
|
1161 |
+
},
|
1162 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1163 |
+
"judge_score": 36.36015325670498,
|
1164 |
+
"success_rate": 1.0
|
1165 |
+
},
|
1166 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1167 |
+
"judge_score": 36.81992337164751,
|
1168 |
+
"success_rate": 1.0
|
1169 |
+
}
|
1170 |
+
}
|
1171 |
+
},
|
1172 |
+
"muchomusic_test": {
|
1173 |
+
"llama3_70b_judge": {
|
1174 |
+
"Qwen-Audio-Chat": {
|
1175 |
+
"judge_score": 59.0564448188711,
|
1176 |
+
"success_rate": 0.9991575400168492
|
1177 |
+
},
|
1178 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1179 |
+
"judge_score": 51.727042965459134,
|
1180 |
+
"success_rate": 1.0
|
1181 |
+
},
|
1182 |
+
"WavLLM_fairseq": {
|
1183 |
+
"judge_score": 44.3133951137321,
|
1184 |
+
"success_rate": 1.0
|
1185 |
+
},
|
1186 |
+
"Qwen2-Audio-7B-Instruct": {
|
1187 |
+
"judge_score": 71.60909856781802,
|
1188 |
+
"success_rate": 1.0
|
1189 |
+
},
|
1190 |
+
"SALMONN_7B": {
|
1191 |
+
"judge_score": 50.88458298230834,
|
1192 |
+
"success_rate": 1.0
|
1193 |
+
},
|
1194 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1195 |
+
"judge_score": 57.7927548441449,
|
1196 |
+
"success_rate": 1.0
|
1197 |
+
},
|
1198 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1199 |
+
"judge_score": 56.44481887110362,
|
1200 |
+
"success_rate": 1.0
|
1201 |
+
}
|
1202 |
+
}
|
1203 |
+
},
|
1204 |
+
"imda_part6_30s_ds_test": {
|
1205 |
+
"llama3_70b_judge": {
|
1206 |
+
"Qwen-Audio-Chat": {
|
1207 |
+
"judge_score": 43.84,
|
1208 |
+
"success_rate": 0.993
|
1209 |
+
},
|
1210 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1211 |
+
"judge_score": 65.6,
|
1212 |
+
"success_rate": 0.996
|
1213 |
+
},
|
1214 |
+
"Qwen2-Audio-7B-Instruct": {
|
1215 |
+
"judge_score": 48.38,
|
1216 |
+
"success_rate": 0.999
|
1217 |
+
},
|
1218 |
+
"SALMONN_7B": {
|
1219 |
+
"judge_score": 27.12,
|
1220 |
+
"success_rate": 1.0
|
1221 |
+
},
|
1222 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1223 |
+
"judge_score": 59.2,
|
1224 |
+
"success_rate": 0.999
|
1225 |
+
}
|
1226 |
+
},
|
1227 |
+
"gpt4o_judge": {
|
1228 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1229 |
+
"judge_score": 67.58,
|
1230 |
+
"success_rate": 1.0
|
1231 |
+
}
|
1232 |
+
}
|
1233 |
+
},
|
1234 |
+
"clotho_aqa_test": {
|
1235 |
+
"llama3_70b_judge": {
|
1236 |
+
"Qwen-Audio-Chat": {
|
1237 |
+
"judge_score": 61.934856587263,
|
1238 |
+
"success_rate": 1.0
|
1239 |
+
},
|
1240 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1241 |
+
"judge_score": 24.647544968400585,
|
1242 |
+
"success_rate": 1.0
|
1243 |
+
},
|
1244 |
+
"WavLLM_fairseq": {
|
1245 |
+
"judge_score": 43.01199466903598,
|
1246 |
+
"success_rate": 0.998223011994669
|
1247 |
+
},
|
1248 |
+
"Qwen2-Audio-7B-Instruct": {
|
1249 |
+
"judge_score": 50.919591292758774,
|
1250 |
+
"success_rate": 0.9991115059973346
|
1251 |
+
},
|
1252 |
+
"SALMONN_7B": {
|
1253 |
+
"judge_score": 57.75401069518716,
|
1254 |
+
"success_rate": 1.0
|
1255 |
+
},
|
1256 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1257 |
+
"judge_score": 63.15021876519203,
|
1258 |
+
"success_rate": 1.0
|
1259 |
+
},
|
1260 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1261 |
+
"judge_score": 29.47134606841404,
|
1262 |
+
"success_rate": 0.9991115059973346
|
1263 |
+
}
|
1264 |
+
},
|
1265 |
+
"gpt4o_judge": {
|
1266 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1267 |
+
"judge_score": 28.076410484229232,
|
1268 |
+
"success_rate": 1.0
|
1269 |
+
}
|
1270 |
+
}
|
1271 |
+
},
|
1272 |
+
"imda_part3_30s_sqa_human_test": {
|
1273 |
+
"llama3_70b_judge": {
|
1274 |
+
"Qwen-Audio-Chat": {
|
1275 |
+
"judge_score": 32.2,
|
1276 |
+
"success_rate": 1.0
|
1277 |
+
},
|
1278 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1279 |
+
"judge_score": 56.0,
|
1280 |
+
"success_rate": 1.0
|
1281 |
+
},
|
1282 |
+
"WavLLM_fairseq": {
|
1283 |
+
"judge_score": 45.199999999999996,
|
1284 |
+
"success_rate": 1.0
|
1285 |
+
},
|
1286 |
+
"Qwen2-Audio-7B-Instruct": {
|
1287 |
+
"judge_score": 42.0,
|
1288 |
+
"success_rate": 1.0
|
1289 |
+
},
|
1290 |
+
"SALMONN_7B": {
|
1291 |
+
"judge_score": 40.599999999999994,
|
1292 |
+
"success_rate": 1.0
|
1293 |
+
},
|
1294 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1295 |
+
"judge_score": 51.4,
|
1296 |
+
"success_rate": 1.0
|
1297 |
+
},
|
1298 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1299 |
+
"judge_score": 49.0,
|
1300 |
+
"success_rate": 1.0
|
1301 |
+
}
|
1302 |
+
},
|
1303 |
+
"gpt4o_judge": {
|
1304 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1305 |
+
"judge_score": 52.800000000000004,
|
1306 |
+
"success_rate": 1.0
|
1307 |
+
}
|
1308 |
+
}
|
1309 |
+
},
|
1310 |
+
"imda_part6_30s_sqa_test": {
|
1311 |
+
"llama3_70b_judge": {
|
1312 |
+
"Qwen-Audio-Chat": {
|
1313 |
+
"judge_score": 63.040000000000006,
|
1314 |
+
"success_rate": 0.998
|
1315 |
+
},
|
1316 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1317 |
+
"judge_score": 83.08,
|
1318 |
+
"success_rate": 1.0
|
1319 |
+
},
|
1320 |
+
"Qwen2-Audio-7B-Instruct": {
|
1321 |
+
"judge_score": 69.42,
|
1322 |
+
"success_rate": 0.998
|
1323 |
+
},
|
1324 |
+
"SALMONN_7B": {
|
1325 |
+
"judge_score": 66.86,
|
1326 |
+
"success_rate": 1.0
|
1327 |
+
},
|
1328 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1329 |
+
"judge_score": 80.60000000000001,
|
1330 |
+
"success_rate": 1.0
|
1331 |
+
}
|
1332 |
+
},
|
1333 |
+
"gpt4o_judge": {
|
1334 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1335 |
+
"judge_score": 81.8,
|
1336 |
+
"success_rate": 0.999
|
1337 |
+
}
|
1338 |
+
}
|
1339 |
+
},
|
1340 |
+
"imda_30s_ds_test": {
|
1341 |
+
"llama3_70b_judge": {
|
1342 |
+
"Qwen-Audio-Chat": {
|
1343 |
+
"judge_score": 31.295,
|
1344 |
+
"success_rate": 0.99625
|
1345 |
+
},
|
1346 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1347 |
+
"judge_score": 54.515,
|
1348 |
+
"success_rate": 0.99575
|
1349 |
+
},
|
1350 |
+
"Qwen2-Audio-7B-Instruct": {
|
1351 |
+
"judge_score": 38.915,
|
1352 |
+
"success_rate": 0.99775
|
1353 |
+
},
|
1354 |
+
"SALMONN_7B": {
|
1355 |
+
"judge_score": 18.345,
|
1356 |
+
"success_rate": 0.999
|
1357 |
+
},
|
1358 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1359 |
+
"judge_score": 48.269999999999996,
|
1360 |
+
"success_rate": 0.998
|
1361 |
+
}
|
1362 |
+
},
|
1363 |
+
"gpt4o_judge": {
|
1364 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1365 |
+
"judge_score": 57.99,
|
1366 |
+
"success_rate": 0.99975
|
1367 |
+
}
|
1368 |
+
}
|
1369 |
+
},
|
1370 |
+
"iemocap_emotion_test": {
|
1371 |
+
"llama3_70b_judge": {
|
1372 |
+
"Qwen-Audio-Chat": {
|
1373 |
+
"judge_score": 29.382470119521916,
|
1374 |
+
"success_rate": 1.0
|
1375 |
+
},
|
1376 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1377 |
+
"judge_score": 44.322709163346616,
|
1378 |
+
"success_rate": 0.99800796812749
|
1379 |
+
},
|
1380 |
+
"WavLLM_fairseq": {
|
1381 |
+
"judge_score": 59.76095617529881,
|
1382 |
+
"success_rate": 0.999003984063745
|
1383 |
+
},
|
1384 |
+
"Qwen2-Audio-7B-Instruct": {
|
1385 |
+
"judge_score": 53.98406374501992,
|
1386 |
+
"success_rate": 1.0
|
1387 |
+
},
|
1388 |
+
"SALMONN_7B": {
|
1389 |
+
"judge_score": 23.804780876494025,
|
1390 |
+
"success_rate": 1.0
|
1391 |
+
},
|
1392 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1393 |
+
"judge_score": 48.505976095617534,
|
1394 |
+
"success_rate": 1.0
|
1395 |
+
},
|
1396 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1397 |
+
"judge_score": 46.713147410358566,
|
1398 |
+
"success_rate": 1.0
|
1399 |
+
}
|
1400 |
+
}
|
1401 |
+
},
|
1402 |
+
"imda_part6_30s_ds_human_test": {
|
1403 |
+
"llama3_70b_judge": {
|
1404 |
+
"Qwen-Audio-Chat": {
|
1405 |
+
"judge_score": 40.4,
|
1406 |
+
"success_rate": 1.0
|
1407 |
+
},
|
1408 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1409 |
+
"judge_score": 65.4,
|
1410 |
+
"success_rate": 1.0
|
1411 |
+
},
|
1412 |
+
"WavLLM_fairseq": {
|
1413 |
+
"judge_score": 49.400000000000006,
|
1414 |
+
"success_rate": 1.0
|
1415 |
+
},
|
1416 |
+
"Qwen2-Audio-7B-Instruct": {
|
1417 |
+
"judge_score": 46.2,
|
1418 |
+
"success_rate": 1.0
|
1419 |
+
},
|
1420 |
+
"SALMONN_7B": {
|
1421 |
+
"judge_score": 24.2,
|
1422 |
+
"success_rate": 1.0
|
1423 |
+
},
|
1424 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1425 |
+
"judge_score": 62.599999999999994,
|
1426 |
+
"success_rate": 1.0
|
1427 |
+
},
|
1428 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1429 |
+
"judge_score": 57.199999999999996,
|
1430 |
+
"success_rate": 1.0
|
1431 |
+
}
|
1432 |
+
},
|
1433 |
+
"gpt4o_judge": {
|
1434 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1435 |
+
"judge_score": 64.4,
|
1436 |
+
"success_rate": 1.0
|
1437 |
+
}
|
1438 |
+
}
|
1439 |
+
},
|
1440 |
+
"imda_30s_sqa_test": {
|
1441 |
+
"llama3_70b_judge": {
|
1442 |
+
"Qwen-Audio-Chat": {
|
1443 |
+
"judge_score": 54.669999999999995,
|
1444 |
+
"success_rate": 0.99875
|
1445 |
+
},
|
1446 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1447 |
+
"judge_score": 75.09,
|
1448 |
+
"success_rate": 0.99875
|
1449 |
+
},
|
1450 |
+
"Qwen2-Audio-7B-Instruct": {
|
1451 |
+
"judge_score": 62.190000000000005,
|
1452 |
+
"success_rate": 0.99925
|
1453 |
+
},
|
1454 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1455 |
+
"judge_score": 72.475,
|
1456 |
+
"success_rate": 0.99925
|
1457 |
+
}
|
1458 |
+
},
|
1459 |
+
"gpt4o_judge": {
|
1460 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1461 |
+
"judge_score": 75.11999999999999,
|
1462 |
+
"success_rate": 0.9995
|
1463 |
+
}
|
1464 |
+
}
|
1465 |
+
},
|
1466 |
+
"wavcaps_qa_test": {
|
1467 |
+
"llama3_70b_judge": {
|
1468 |
+
"Qwen-Audio-Chat": {
|
1469 |
+
"judge_score": 42.69736842105263,
|
1470 |
+
"success_rate": 1.0
|
1471 |
+
},
|
1472 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1473 |
+
"judge_score": 18.88157894736842,
|
1474 |
+
"success_rate": 1.0
|
1475 |
+
},
|
1476 |
+
"WavLLM_fairseq": {
|
1477 |
+
"judge_score": 26.25,
|
1478 |
+
"success_rate": 0.9967105263157895
|
1479 |
+
},
|
1480 |
+
"Qwen2-Audio-7B-Instruct": {
|
1481 |
+
"judge_score": 44.473684210526315,
|
1482 |
+
"success_rate": 0.9967105263157895
|
1483 |
+
},
|
1484 |
+
"SALMONN_7B": {
|
1485 |
+
"judge_score": 47.30263157894737,
|
1486 |
+
"success_rate": 1.0
|
1487 |
+
},
|
1488 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1489 |
+
"judge_score": 46.31578947368421,
|
1490 |
+
"success_rate": 1.0
|
1491 |
+
},
|
1492 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1493 |
+
"judge_score": 16.710526315789473,
|
1494 |
+
"success_rate": 1.0
|
1495 |
+
}
|
1496 |
+
},
|
1497 |
+
"gpt4o_judge": {
|
1498 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1499 |
+
"judge_score": 14.736842105263158,
|
1500 |
+
"success_rate": 1.0
|
1501 |
+
}
|
1502 |
+
}
|
1503 |
+
},
|
1504 |
+
"wavcaps_test": {
|
1505 |
+
"meteor": {
|
1506 |
+
"Qwen-Audio-Chat": 0.2355106805560457,
|
1507 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.120421856260385,
|
1508 |
+
"WavLLM_fairseq": 0.06399522524688675,
|
1509 |
+
"Qwen2-Audio-7B-Instruct": 0.21342294856199182,
|
1510 |
+
"SALMONN_7B": 0.17175112770658157,
|
1511 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": 0.3175511907248581,
|
1512 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.1388630786594543
|
1513 |
+
},
|
1514 |
+
"llama3_70b_judge": {
|
1515 |
+
"Qwen-Audio-Chat": {
|
1516 |
+
"judge_score": 32.9364161849711,
|
1517 |
+
"success_rate": 0.999421965317919
|
1518 |
+
},
|
1519 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1520 |
+
"judge_score": 6.3468208092485545,
|
1521 |
+
"success_rate": 1.0
|
1522 |
+
},
|
1523 |
+
"WavLLM_fairseq": {
|
1524 |
+
"judge_score": 6.901734104046243,
|
1525 |
+
"success_rate": 0.9976878612716763
|
1526 |
+
},
|
1527 |
+
"Qwen2-Audio-7B-Instruct": {
|
1528 |
+
"judge_score": 33.78034682080925,
|
1529 |
+
"success_rate": 0.9976878612716763
|
1530 |
+
},
|
1531 |
+
"SALMONN_7B": {
|
1532 |
+
"judge_score": 23.76878612716763,
|
1533 |
+
"success_rate": 0.999421965317919
|
1534 |
+
},
|
1535 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1536 |
+
"judge_score": 33.97687861271676,
|
1537 |
+
"success_rate": 0.999421965317919
|
1538 |
+
},
|
1539 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1540 |
+
"judge_score": 3.445086705202312,
|
1541 |
+
"success_rate": 0.9988439306358381
|
1542 |
+
}
|
1543 |
+
},
|
1544 |
+
"gpt4o_judge": {
|
1545 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1546 |
+
"judge_score": 4.61271676300578,
|
1547 |
+
"success_rate": 0.999421965317919
|
1548 |
+
}
|
1549 |
+
}
|
1550 |
+
},
|
1551 |
+
"imda_part3_30s_ds_test": {
|
1552 |
+
"llama3_70b_judge": {
|
1553 |
+
"Qwen-Audio-Chat": {
|
1554 |
+
"judge_score": 25.22,
|
1555 |
+
"success_rate": 0.997
|
1556 |
+
},
|
1557 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1558 |
+
"judge_score": 48.339999999999996,
|
1559 |
+
"success_rate": 0.998
|
1560 |
+
},
|
1561 |
+
"WavLLM_fairseq": {
|
1562 |
+
"judge_score": 36.5,
|
1563 |
+
"success_rate": 0.997
|
1564 |
+
},
|
1565 |
+
"Qwen2-Audio-7B-Instruct": {
|
1566 |
+
"judge_score": 35.54,
|
1567 |
+
"success_rate": 0.996
|
1568 |
+
},
|
1569 |
+
"SALMONN_7B": {
|
1570 |
+
"judge_score": 12.82,
|
1571 |
+
"success_rate": 0.998
|
1572 |
+
},
|
1573 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1574 |
+
"judge_score": 42.32,
|
1575 |
+
"success_rate": 0.998
|
1576 |
+
}
|
1577 |
+
},
|
1578 |
+
"gpt4o_judge": {
|
1579 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1580 |
+
"judge_score": 52.38,
|
1581 |
+
"success_rate": 1.0
|
1582 |
+
}
|
1583 |
+
}
|
1584 |
+
},
|
1585 |
+
"meld_sentiment_test": {
|
1586 |
+
"llama3_70b_judge": {
|
1587 |
+
"Qwen-Audio-Chat": {
|
1588 |
+
"judge_score": 44.90421455938697,
|
1589 |
+
"success_rate": 1.0
|
1590 |
+
},
|
1591 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1592 |
+
"judge_score": 56.59003831417625,
|
1593 |
+
"success_rate": 1.0
|
1594 |
+
},
|
1595 |
+
"WavLLM_fairseq": {
|
1596 |
+
"judge_score": 51.072796934865906,
|
1597 |
+
"success_rate": 0.9996168582375479
|
1598 |
+
},
|
1599 |
+
"Qwen2-Audio-7B-Instruct": {
|
1600 |
+
"judge_score": 53.9463601532567,
|
1601 |
+
"success_rate": 1.0
|
1602 |
+
},
|
1603 |
+
"SALMONN_7B": {
|
1604 |
+
"judge_score": 41.7624521072797,
|
1605 |
+
"success_rate": 0.9996168582375479
|
1606 |
+
},
|
1607 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1608 |
+
"judge_score": 46.206896551724135,
|
1609 |
+
"success_rate": 1.0
|
1610 |
+
},
|
1611 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1612 |
+
"judge_score": 45.593869731800766,
|
1613 |
+
"success_rate": 0.9996168582375479
|
1614 |
+
}
|
1615 |
+
}
|
1616 |
+
},
|
1617 |
+
"imda_part5_30s_ds_human_test": {
|
1618 |
+
"llama3_70b_judge": {
|
1619 |
+
"Qwen-Audio-Chat": {
|
1620 |
+
"judge_score": 28.2,
|
1621 |
+
"success_rate": 1.0
|
1622 |
+
},
|
1623 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1624 |
+
"judge_score": 58.0,
|
1625 |
+
"success_rate": 1.0
|
1626 |
+
},
|
1627 |
+
"WavLLM_fairseq": {
|
1628 |
+
"judge_score": 45.199999999999996,
|
1629 |
+
"success_rate": 1.0
|
1630 |
+
},
|
1631 |
+
"Qwen2-Audio-7B-Instruct": {
|
1632 |
+
"judge_score": 40.4,
|
1633 |
+
"success_rate": 1.0
|
1634 |
+
},
|
1635 |
+
"SALMONN_7B": {
|
1636 |
+
"judge_score": 17.2,
|
1637 |
+
"success_rate": 0.99
|
1638 |
+
},
|
1639 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1640 |
+
"judge_score": 57.0,
|
1641 |
+
"success_rate": 0.99
|
1642 |
+
},
|
1643 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1644 |
+
"judge_score": 49.0,
|
1645 |
+
"success_rate": 0.99
|
1646 |
+
}
|
1647 |
+
},
|
1648 |
+
"gpt4o_judge": {
|
1649 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1650 |
+
"judge_score": 56.8,
|
1651 |
+
"success_rate": 1.0
|
1652 |
+
}
|
1653 |
+
}
|
1654 |
+
},
|
1655 |
+
"imda_part5_30s_sqa_test": {
|
1656 |
+
"llama3_70b_judge": {
|
1657 |
+
"Qwen-Audio-Chat": {
|
1658 |
+
"judge_score": 61.260000000000005,
|
1659 |
+
"success_rate": 1.0
|
1660 |
+
},
|
1661 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1662 |
+
"judge_score": 80.34,
|
1663 |
+
"success_rate": 0.999
|
1664 |
+
},
|
1665 |
+
"Qwen2-Audio-7B-Instruct": {
|
1666 |
+
"judge_score": 68.52000000000001,
|
1667 |
+
"success_rate": 0.999
|
1668 |
+
},
|
1669 |
+
"SALMONN_7B": {
|
1670 |
+
"judge_score": 62.62,
|
1671 |
+
"success_rate": 1.0
|
1672 |
+
},
|
1673 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1674 |
+
"judge_score": 76.56,
|
1675 |
+
"success_rate": 1.0
|
1676 |
+
}
|
1677 |
+
},
|
1678 |
+
"gpt4o_judge": {
|
1679 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1680 |
+
"judge_score": 80.36,
|
1681 |
+
"success_rate": 1.0
|
1682 |
+
}
|
1683 |
+
}
|
1684 |
+
},
|
1685 |
+
"voxceleb_accent_test": {
|
1686 |
+
"llama3_70b_judge": {
|
1687 |
+
"Qwen-Audio-Chat": {
|
1688 |
+
"judge_score": 48.05088223225277,
|
1689 |
+
"success_rate": 0.9995896594173164
|
1690 |
+
},
|
1691 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1692 |
+
"judge_score": 24.640951990151827,
|
1693 |
+
"success_rate": 0.9997948297086582
|
1694 |
+
},
|
1695 |
+
"WavLLM_fairseq": {
|
1696 |
+
"judge_score": 39.96717275338531,
|
1697 |
+
"success_rate": 0.9993844891259746
|
1698 |
+
},
|
1699 |
+
"Qwen2-Audio-7B-Instruct": {
|
1700 |
+
"judge_score": 29.187525646286417,
|
1701 |
+
"success_rate": 1.0
|
1702 |
+
},
|
1703 |
+
"SALMONN_7B": {
|
1704 |
+
"judge_score": 34.222404595814524,
|
1705 |
+
"success_rate": 0.9993844891259746
|
1706 |
+
},
|
1707 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1708 |
+
"judge_score": 47.01682396389003,
|
1709 |
+
"success_rate": 0.9997948297086582
|
1710 |
+
},
|
1711 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1712 |
+
"judge_score": 39.32704144439885,
|
1713 |
+
"success_rate": 0.9993844891259746
|
1714 |
+
}
|
1715 |
+
},
|
1716 |
+
"gpt4o_judge": {
|
1717 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1718 |
+
"judge_score": 39.462453836684446,
|
1719 |
+
"success_rate": 1.0
|
1720 |
+
}
|
1721 |
+
}
|
1722 |
+
},
|
1723 |
+
"audiocaps_qa_test": {
|
1724 |
+
"llama3_70b_judge": {
|
1725 |
+
"Qwen-Audio-Chat": {
|
1726 |
+
"judge_score": 50.22364217252396,
|
1727 |
+
"success_rate": 1.0
|
1728 |
+
},
|
1729 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1730 |
+
"judge_score": 18.466453674121407,
|
1731 |
+
"success_rate": 1.0
|
1732 |
+
},
|
1733 |
+
"WavLLM_fairseq": {
|
1734 |
+
"judge_score": 29.840255591054312,
|
1735 |
+
"success_rate": 1.0
|
1736 |
+
},
|
1737 |
+
"Qwen2-Audio-7B-Instruct": {
|
1738 |
+
"judge_score": 45.75079872204473,
|
1739 |
+
"success_rate": 1.0
|
1740 |
+
},
|
1741 |
+
"SALMONN_7B": {
|
1742 |
+
"judge_score": 50.287539936102235,
|
1743 |
+
"success_rate": 1.0
|
1744 |
+
},
|
1745 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1746 |
+
"judge_score": 49.77635782747604,
|
1747 |
+
"success_rate": 1.0
|
1748 |
+
},
|
1749 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1750 |
+
"judge_score": 17.380191693290733,
|
1751 |
+
"success_rate": 1.0
|
1752 |
+
}
|
1753 |
+
},
|
1754 |
+
"gpt4o_judge": {
|
1755 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1756 |
+
"judge_score": 14.63258785942492,
|
1757 |
+
"success_rate": 1.0
|
1758 |
+
}
|
1759 |
+
}
|
1760 |
+
},
|
1761 |
+
"public_sg_speech_qa_test": {
|
1762 |
+
"llama3_70b_judge": {
|
1763 |
+
"Qwen-Audio-Chat": {
|
1764 |
+
"judge_score": 63.16860465116279,
|
1765 |
+
"success_rate": 0.9941860465116279
|
1766 |
+
},
|
1767 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1768 |
+
"judge_score": 73.11046511627907,
|
1769 |
+
"success_rate": 0.998546511627907
|
1770 |
+
},
|
1771 |
+
"WavLLM_fairseq": {
|
1772 |
+
"judge_score": 58.54651162790698,
|
1773 |
+
"success_rate": 0.9825581395348837
|
1774 |
+
},
|
1775 |
+
"Qwen2-Audio-7B-Instruct": {
|
1776 |
+
"judge_score": 58.31395348837209,
|
1777 |
+
"success_rate": 0.9927325581395349
|
1778 |
+
},
|
1779 |
+
"SALMONN_7B": {
|
1780 |
+
"judge_score": 59.24418604651163,
|
1781 |
+
"success_rate": 0.997093023255814
|
1782 |
+
},
|
1783 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1784 |
+
"judge_score": 59.7093023255814,
|
1785 |
+
"success_rate": 0.997093023255814
|
1786 |
+
},
|
1787 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1788 |
+
"judge_score": 64.94186046511628,
|
1789 |
+
"success_rate": 0.9927325581395349
|
1790 |
+
}
|
1791 |
+
},
|
1792 |
+
"gpt4o_judge": {
|
1793 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1794 |
+
"judge_score": 73.02325581395348,
|
1795 |
+
"success_rate": 1.0
|
1796 |
+
}
|
1797 |
+
}
|
1798 |
+
},
|
1799 |
+
"imda_30s_ds_human_test": {
|
1800 |
+
"llama3_70b_judge": {
|
1801 |
+
"Qwen-Audio-Chat": {
|
1802 |
+
"judge_score": 30.65,
|
1803 |
+
"success_rate": 0.995
|
1804 |
+
},
|
1805 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1806 |
+
"judge_score": 50.15,
|
1807 |
+
"success_rate": 0.9975
|
1808 |
+
},
|
1809 |
+
"Qwen2-Audio-7B-Instruct": {
|
1810 |
+
"judge_score": 37.599999999999994,
|
1811 |
+
"success_rate": 0.995
|
1812 |
+
},
|
1813 |
+
"SALMONN_7B": {
|
1814 |
+
"judge_score": 16.15,
|
1815 |
+
"success_rate": 0.9975
|
1816 |
+
},
|
1817 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1818 |
+
"judge_score": 43.849999999999994,
|
1819 |
+
"success_rate": 1.0
|
1820 |
+
}
|
1821 |
+
},
|
1822 |
+
"gpt4o_judge": {
|
1823 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1824 |
+
"judge_score": 54.65,
|
1825 |
+
"success_rate": 1.0
|
1826 |
+
}
|
1827 |
+
}
|
1828 |
+
},
|
1829 |
+
"alpaca_audio_test": {
|
1830 |
+
"llama3_70b_judge": {
|
1831 |
+
"Qwen-Audio-Chat": {
|
1832 |
+
"judge_score": 9.8,
|
1833 |
+
"success_rate": 1.0
|
1834 |
+
},
|
1835 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1836 |
+
"judge_score": 73.8,
|
1837 |
+
"success_rate": 1.0
|
1838 |
+
},
|
1839 |
+
"WavLLM_fairseq": {
|
1840 |
+
"judge_score": 21.6,
|
1841 |
+
"success_rate": 0.99
|
1842 |
+
},
|
1843 |
+
"Qwen2-Audio-7B-Instruct": {
|
1844 |
+
"judge_score": 52.599999999999994,
|
1845 |
+
"success_rate": 0.99
|
1846 |
+
},
|
1847 |
+
"SALMONN_7B": {
|
1848 |
+
"judge_score": 17.2,
|
1849 |
+
"success_rate": 1.0
|
1850 |
+
},
|
1851 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1852 |
+
"judge_score": 74.80000000000001,
|
1853 |
+
"success_rate": 0.99
|
1854 |
+
},
|
1855 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1856 |
+
"judge_score": 70.8,
|
1857 |
+
"success_rate": 0.96
|
1858 |
+
}
|
1859 |
+
},
|
1860 |
+
"gpt4o_judge": {
|
1861 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1862 |
+
"judge_score": 77.8,
|
1863 |
+
"success_rate": 1.0
|
1864 |
+
}
|
1865 |
+
}
|
1866 |
+
},
|
1867 |
+
"imda_30s_sqa_human_test": {
|
1868 |
+
"llama3_70b_judge": {
|
1869 |
+
"Qwen-Audio-Chat": {
|
1870 |
+
"judge_score": 42.199999999999996,
|
1871 |
+
"success_rate": 1.0
|
1872 |
+
},
|
1873 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1874 |
+
"judge_score": 62.95,
|
1875 |
+
"success_rate": 0.9975
|
1876 |
+
},
|
1877 |
+
"Qwen2-Audio-7B-Instruct": {
|
1878 |
+
"judge_score": 47.1,
|
1879 |
+
"success_rate": 0.995
|
1880 |
+
},
|
1881 |
+
"SALMONN_7B": {
|
1882 |
+
"judge_score": 42.300000000000004,
|
1883 |
+
"success_rate": 1.0
|
1884 |
+
},
|
1885 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1886 |
+
"judge_score": 55.7,
|
1887 |
+
"success_rate": 1.0
|
1888 |
+
}
|
1889 |
+
},
|
1890 |
+
"gpt4o_judge": {
|
1891 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1892 |
+
"judge_score": 61.550000000000004,
|
1893 |
+
"success_rate": 1.0
|
1894 |
+
}
|
1895 |
+
}
|
1896 |
+
},
|
1897 |
+
"imda_part4_30s_ds_human_test": {
|
1898 |
+
"llama3_70b_judge": {
|
1899 |
+
"Qwen-Audio-Chat": {
|
1900 |
+
"judge_score": 16.0,
|
1901 |
+
"success_rate": 0.99
|
1902 |
+
},
|
1903 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1904 |
+
"judge_score": 44.0,
|
1905 |
+
"success_rate": 1.0
|
1906 |
+
},
|
1907 |
+
"WavLLM_fairseq": {
|
1908 |
+
"judge_score": 31.6,
|
1909 |
+
"success_rate": 1.0
|
1910 |
+
},
|
1911 |
+
"Qwen2-Audio-7B-Instruct": {
|
1912 |
+
"judge_score": 24.8,
|
1913 |
+
"success_rate": 0.97
|
1914 |
+
},
|
1915 |
+
"SALMONN_7B": {
|
1916 |
+
"judge_score": 7.0,
|
1917 |
+
"success_rate": 0.99
|
1918 |
+
},
|
1919 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1920 |
+
"judge_score": 46.4,
|
1921 |
+
"success_rate": 1.0
|
1922 |
+
},
|
1923 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1924 |
+
"judge_score": 36.0,
|
1925 |
+
"success_rate": 0.99
|
1926 |
+
}
|
1927 |
+
},
|
1928 |
+
"gpt4o_judge": {
|
1929 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1930 |
+
"judge_score": 48.2,
|
1931 |
+
"success_rate": 1.0
|
1932 |
+
}
|
1933 |
+
}
|
1934 |
+
},
|
1935 |
+
"imda_part4_30s_sqa_human_test": {
|
1936 |
+
"llama3_70b_judge": {
|
1937 |
+
"Qwen-Audio-Chat": {
|
1938 |
+
"judge_score": 37.8,
|
1939 |
+
"success_rate": 1.0
|
1940 |
+
},
|
1941 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1942 |
+
"judge_score": 66.0,
|
1943 |
+
"success_rate": 1.0
|
1944 |
+
},
|
1945 |
+
"WavLLM_fairseq": {
|
1946 |
+
"judge_score": 46.6,
|
1947 |
+
"success_rate": 1.0
|
1948 |
+
},
|
1949 |
+
"Qwen2-Audio-7B-Instruct": {
|
1950 |
+
"judge_score": 39.6,
|
1951 |
+
"success_rate": 1.0
|
1952 |
+
},
|
1953 |
+
"SALMONN_7B": {
|
1954 |
+
"judge_score": 36.6,
|
1955 |
+
"success_rate": 1.0
|
1956 |
+
},
|
1957 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1958 |
+
"judge_score": 53.2,
|
1959 |
+
"success_rate": 1.0
|
1960 |
+
},
|
1961 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1962 |
+
"judge_score": 53.8,
|
1963 |
+
"success_rate": 1.0
|
1964 |
+
}
|
1965 |
+
},
|
1966 |
+
"gpt4o_judge": {
|
1967 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
1968 |
+
"judge_score": 61.4,
|
1969 |
+
"success_rate": 1.0
|
1970 |
+
}
|
1971 |
+
}
|
1972 |
+
},
|
1973 |
+
"iemocap_gender_test": {
|
1974 |
+
"llama3_70b_judge": {
|
1975 |
+
"Qwen-Audio-Chat": {
|
1976 |
+
"judge_score": 50.0996015936255,
|
1977 |
+
"success_rate": 1.0
|
1978 |
+
},
|
1979 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
1980 |
+
"judge_score": 15.737051792828685,
|
1981 |
+
"success_rate": 1.0
|
1982 |
+
},
|
1983 |
+
"WavLLM_fairseq": {
|
1984 |
+
"judge_score": 51.932270916334666,
|
1985 |
+
"success_rate": 1.0
|
1986 |
+
},
|
1987 |
+
"Qwen2-Audio-7B-Instruct": {
|
1988 |
+
"judge_score": 92.80876494023903,
|
1989 |
+
"success_rate": 1.0
|
1990 |
+
},
|
1991 |
+
"SALMONN_7B": {
|
1992 |
+
"judge_score": 81.31474103585658,
|
1993 |
+
"success_rate": 1.0
|
1994 |
+
},
|
1995 |
+
"MERaLiON-AudioLLM-Whisper-SEA-LION": {
|
1996 |
+
"judge_score": 93.48605577689243,
|
1997 |
+
"success_rate": 1.0
|
1998 |
+
},
|
1999 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
2000 |
+
"judge_score": 44.22310756972111,
|
2001 |
+
"success_rate": 1.0
|
2002 |
+
}
|
2003 |
+
}
|
2004 |
+
},
|
2005 |
+
"imda_30s_gr_test": {
|
2006 |
+
"llama3_70b_judge": {
|
2007 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
2008 |
+
"judge_score": 18.46666666666667,
|
2009 |
+
"success_rate": 1.0
|
2010 |
+
}
|
2011 |
+
}
|
2012 |
+
},
|
2013 |
+
"imda_30s_ar_test": {
|
2014 |
+
"llama3_70b_judge": {
|
2015 |
+
"cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": {
|
2016 |
+
"judge_score": 15.773333333333333,
|
2017 |
+
"success_rate": 0.9996666666666667
|
2018 |
+
},
|
2019 |
+
"Qwen2-Audio-7B-Instruct": {
|
2020 |
+
"judge_score": 5.106666666666667,
|
2021 |
+
"success_rate": 1.0
|
2022 |
+
},
|
2023 |
+
"SALMONN_7B": {
|
2024 |
+
"judge_score": 5.673333333333334,
|
2025 |
+
"success_rate": 1.0
|
2026 |
+
},
|
2027 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": {
|
2028 |
+
"judge_score": 27.186666666666667,
|
2029 |
+
"success_rate": 0.9996666666666667
|
2030 |
+
}
|
2031 |
+
}
|
2032 |
+
},
|
2033 |
+
"mmau_mini": {
|
2034 |
+
"llama3_70b_judge": {
|
2035 |
+
"phi_4_multimodal_instruct": {
|
2036 |
+
"judge_score": 59.4,
|
2037 |
+
"success_rate": 1.0
|
2038 |
+
}
|
2039 |
+
}
|
2040 |
+
},
|
2041 |
+
"nlb_asr_test": {
|
2042 |
+
"wer": {
|
2043 |
+
"cascade_whisper_large_v3_llama_3_8b_instruct": 0.2796380263880551
|
2044 |
+
}
|
2045 |
+
}
|
2046 |
+
}
|