|
Model,imda_part3_30s_ds_human_test,imda_part4_30s_ds_human_test,imda_part5_30s_ds_human_test,imda_part6_30s_ds_human_test |
|
Qwen-Audio-Chat,16.4,16.0,28.2,40.4 |
|
hy_whisper_local_cs,,,, |
|
Qwen2-Audio-7B-Instruct,33.8,24.8,40.4,46.2 |
|
whisper_large_v3,,,, |
|
old_models,,,, |
|
gemini-1.5-flash,,,, |
|
WavLLM_fairseq,31.6,31.6,45.2,49.400000000000006 |
|
MERaLiON-AudioLLM-Whisper-SEA-LION,47.800000000000004,46.4,54.6,65.6 |
|
MERaLiON-AudioLLM-v2-2b,42.2,40.199999999999996,51.8,60.0 |
|
MERaLiON-AudioLLM-v2-9b,49.8,46.6,55.4,60.599999999999994 |
|
MERaLiON-AudioLLM-v2-9b-asr,53.0,49.6,58.2,62.400000000000006 |
|
Qwen2.5-Omni-3B,42.800000000000004,33.199999999999996,52.199999999999996,58.8 |
|
Qwen2.5-Omni-7B,39.8,31.6,42.800000000000004,58.4 |
|
SALMONN_7B,9.0,7.4,16.0,25.2 |
|
SeaLLMs-Audio-7B,42.0,35.2,49.6,55.0 |
|
cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct,48.4,45.599999999999994,53.4,56.6 |
|
cascade_whisper_large_v3_llama_3_8b_instruct,38.0,38.199999999999996,46.2,61.0 |
|
phi_4_multimodal_instruct,43.6,42.800000000000004,55.599999999999994,61.0 |
|
|