|
Model,imda_part3_30s_sqa_human_test,imda_part4_30s_sqa_human_test,imda_part5_30s_sqa_human_test,imda_part6_30s_sqa_human_test |
|
Qwen-Audio-Chat,32.2,37.8,47.8,51.4 |
|
hy_whisper_local_cs,,,, |
|
Qwen2-Audio-7B-Instruct,42.0,39.6,51.6,53.6 |
|
whisper_large_v3,,,, |
|
old_models,,,, |
|
gemini-1.5-flash,,,, |
|
WavLLM_fairseq,45.2,46.6,50.8,62.2 |
|
MERaLiON-AudioLLM-Whisper-SEA-LION,55.199999999999996,50.0,63.0,67.4 |
|
MERaLiON-AudioLLM-v2-2b,52.599999999999994,54.6,61.4,70.19999999999999 |
|
MERaLiON-AudioLLM-v2-9b,59.400000000000006,63.0,72.0,71.8 |
|
Qwen2.5-Omni-3B,52.400000000000006,54.400000000000006,66.0,69.2 |
|
Qwen2.5-Omni-7B,54.2,52.0,62.800000000000004,64.6 |
|
SALMONN_7B,42.0,35.4,45.8,49.6 |
|
cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct,51.4,46.4,54.6,62.599999999999994 |
|
cascade_whisper_large_v3_llama_3_8b_instruct,51.6,55.599999999999994,62.0,68.2 |
|
phi_4_multimodal_instruct,55.0,56.4,64.6,71.8 |
|
|