Model,imda_part1_asr_test,imda_part2_asr_test,imda_part3_30s_asr_test,imda_part4_30s_asr_test,imda_part5_30s_asr_test,imda_part6_30s_asr_test
Qwen-Audio-Chat,0.1055031331529027,0.4547926304683061,0.6412550574306894,1.173131813552289,0.3016882870525747,0.3139424086306303
Qwen2-Audio-7B-Instruct,0.0719771779679613,0.1905689473257041,0.3507616694273223,0.5613424034000176,0.2785600677065853,0.2245352799625317
old_models,,,,,,
gemini-1.5-flash,,,,,,
WavLLM_fairseq,0.1007729256577182,0.4463923382842302,0.7540934640345399,1.143645714142011,0.3979658840524726,0.4254106170965293
MERaLiON-AudioLLM-Whisper-SEA-LION,0.04303513520103382,0.0473581689797906,0.21299589974746788,0.29660878421707804,0.15406166552363165,0.1087388362215152
MERaLiON-AudioLLM-v2-2b,0.049057615877892376,0.05819332846359873,0.26414044043772233,0.3595795244502006,0.20202536078562985,0.1493725673864242
MERaLiON-AudioLLM-v2-9b,0.051959134908443665,0.14532099667234802,0.22654574089662477,0.2948987161915779,0.16760298259181977,0.12655243140231592
MERaLiON-AudioLLM-v2-9b-asr,0.04362031550971643,0.054094635175716256,0.19622831075026476,0.24570911239925058,0.1403598371539887,0.0989680065892537
Qwen2.5-Omni-3B,0.05298320044863824,0.0947975002029056,0.47520840687539034,1.2504495215581737,0.27988793392771155,0.18302944168994978
Qwen2.5-Omni-7B,0.05291005291005291,0.09410762113464816,0.5354359573139272,1.3034993524374756,0.37375786140578715,0.27471373891697215
SALMONN_7B,0.09275107892619414,0.45783621459297136,0.681280039101746,0.7865181254636674,0.37533379054734356,0.25522053004731987
SeaLLMs-Audio-7B,0.12898349303879258,0.2900738576414252,1.195359383061341,1.8651561065774749,0.6310282937648656,0.6653369724963258
cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct,0.07053860970911661,0.3298433568703839,0.2810437993863198,0.4594298934979693,0.21829536997854984,0.17514817745764627
cascade_whisper_large_v3_llama_3_8b_instruct,0.06922195401458074,0.31912994075156237,0.2770250088250468,0.4581096203900464,0.21391778902978215,0.1722411537654032
hy_whisper_local_cs,0.06692999780557385,0.2735167600032465,0.25580416542210876,0.3612895924757007,0.186411988735025,0.14417222500363377
phi_4_multimodal_instruct,0.057615877892375586,0.3451018586153721,0.4381839411301491,1.4697028756805695,0.23859275364433613,0.1439784234241509
whisper_large_v3,0.06919757150171897,0.319251684116549,0.26719526434409535,0.4567139031045279,0.2108972581751324,0.17041618889193946