Upload folder using huggingface_hub

results/bleu/st.csv

@@ -1 +1,6 @@
 Model,covost2_en_id_test,covost2_en_zh_test,covost2_en_ta_test,covost2_id_en_test,covost2_zh_en_test,covost2_ta_en_test
+salmonn_7b,14.135708265627702,34.055681569415356,0.00045042243733421275,27.877196356747618,5.2319724257915645,0.4256092994569619
+wavllm_fairseq,13.841886973016162,31.96381187282953,0.0033159224040994286,5.933522277713613,2.368659001743569,0.1695522548322915
+Qwen2-Audio-7B-Instruct,16.325186897428104,25.765420247070075,0.03245972071872916,6.326113431899141,16.466557744958333,0.04425838146050298
+whisper_large_v3_with_llama_3_8b_instruct,,,,,,
+qwen_audio_chat,4.121393814607146,15.307536203629063,0.030392249793261363,0.5089433695608178,10.019503192969147,0.018955183488794443

results/llama3_70b_judge/ac.csv

@@ -1 +1,6 @@
 Model,audiocaps_test,wavcaps_test
+salmonn_7b,34.372727272727275,21.15606936416185
+wavllm_fairseq,5.5,6.901734104046243
+Qwen2-Audio-7B-Instruct,40.77727272727273,33.78034682080925
+whisper_large_v3_with_llama_3_8b_instruct,2.4727272727272727,3.445086705202312
+qwen_audio_chat,43.82272727272727,29.248554913294797

results/llama3_70b_judge/aqa.csv

@@ -1 +1,6 @@
 Model,clotho_aqa_test,audiocaps_qa_test,wavcaps_qa_test
+salmonn_7b,55.75299866725899,47.02875399361022,46.25
+wavllm_fairseq,43.01199466903598,29.840255591054312,26.25
+Qwen2-Audio-7B-Instruct,50.919591292758774,45.75079872204473,44.473684210526315
+whisper_large_v3_with_llama_3_8b_instruct,29.47134606841404,17.380191693290733,16.710526315789473
+qwen_audio_chat,58.196357174589075,47.98722044728435,38.68421052631579

results/llama3_70b_judge/ar.csv

@@ -1 +1,6 @@
 Model,voxceleb_accent_test
+salmonn_7b,37.443578169881
+wavllm_fairseq,
+Qwen2-Audio-7B-Instruct,29.187525646286417
+whisper_large_v3_with_llama_3_8b_instruct,39.32704144439885
+qwen_audio_chat,45.699630693475584

results/llama3_70b_judge/si.csv

@@ -1 +1,6 @@
 Model,openhermes_audio_test,alpaca_audio_test
+salmonn_7b,19.2,12.4
+wavllm_fairseq,22.400000000000002,21.6
+Qwen2-Audio-7B-Instruct,44.800000000000004,52.599999999999994
+whisper_large_v3_with_llama_3_8b_instruct,63.0,70.8
+qwen_audio_chat,11.0,9.6

results/llama3_70b_judge/sqa.csv

@@ -1 +1,6 @@
 Model,slue_p2_sqa5_test,public_sg_speech_qa_test,spoken_squad_v1
+salmonn_7b,78.23529411764706,56.77325581395348,
+wavllm_fairseq,83.92156862745098,58.54651162790698,
+Qwen2-Audio-7B-Instruct,80.04901960784315,58.31395348837209,
+whisper_large_v3_with_llama_3_8b_instruct,82.99019607843137,64.94186046511628,
+qwen_audio_chat,76.12745098039215,57.47093023255814,

results/llama3_70b_judge_binary/er.csv

@@ -1 +1,6 @@
 Model,iemocap_emotion_test,meld_sentiment_test,meld_emotion_test
+salmonn_7b,21.55688622754491,41.877394636015325,33.06513409961686
+wavllm_fairseq,45.90818363273453,50.076628352490424,41.0727969348659
+Qwen2-Audio-7B-Instruct,49.30139720558882,53.486590038314176,40.536398467432946
+whisper_large_v3_with_llama_3_8b_instruct,34.4311377245509,43.86973180076628,33.25670498084291
+qwen_audio_chat,27.345309381237527,43.86973180076628,50.57471264367817

results/llama3_70b_judge_binary/gr.csv

@@ -1 +1,6 @@
 Model,voxceleb_gender_test,iemocap_gender_test
+salmonn_7b,88.90028723840788,51.59680638722555
+wavllm_fairseq,69.67583093967994,
+Qwen2-Audio-7B-Instruct,99.1177677472302,49.30139720558882
+whisper_large_v3_with_llama_3_8b_instruct,53.40582683627411,51.49700598802395
+qwen_audio_chat,70.55806319244974,51.796407185628745

results/llama3_70b_judge_binary/sqa.csv

@@ -1 +1,6 @@
 Model,cn_college_listen_mcq_test,dream_tts_mcq_test
+salmonn_7b,50.5063848524879,55.933089388395196
+wavllm_fairseq,65.43372963452224,64.55828541557763
+Qwen2-Audio-7B-Instruct,74.50462351387054,66.70151594354418
+whisper_large_v3_with_llama_3_8b_instruct,85.24878907970057,86.0951385258756
+qwen_audio_chat,60.85424922941436,57.76267642446419

results/meteor/ac.csv

@@ -1 +1,6 @@
 Model,audiocaps_test,wavcaps_test
+salmonn_7b,,
+wavllm_fairseq,,
+Qwen2-Audio-7B-Instruct,,
+whisper_large_v3_with_llama_3_8b_instruct,,
+qwen_audio_chat,,

results/wer/asr.csv

@@ -1 +1,6 @@
 Model,librispeech_test_clean,librispeech_test_other,common_voice_15_en_test,peoples_speech_test,gigaspeech_test,earnings21_test,earnings22_test,tedlium3_test,tedlium3_long_form_test,imda_part1_asr_test,imda_part2_asr_test,imda_part3_asr_test,imda_part4_asr_test,imda_part5_asr_test,imda_part6_asr_test
+salmonn_7b,0.555834307918663,0.4180490665254317,0.3375363911542985,0.34335568653146914,0.14226764839341272,0.2687240831119165,0.3638199574803293,0.08558958163301515,0.18386810849140223,0.1581255622670608,0.6915082052617869,0.8632952723448728,1.0998724881343125,0.7462024043822395,0.5240368577507283
+wavllm_fairseq,0.02103218017882069,0.04798834811886432,0.14533325621300636,0.3792176325635977,0.15491778414546403,0.6447482518259942,0.6671766188447099,0.06621482559171073,0.4536784258110264,0.07762498393522684,0.4511070591299818,0.8449539438237986,,0.652558845214085,0.5275247040334478
+Qwen2-Audio-7B-Instruct,0.03201041234390915,0.06073732195887794,0.11438872500819404,0.22323599266520214,0.11891779417331638,0.9865371146513101,0.9884312836905533,0.06387282211419042,0.953518879631271,,,,,,
+whisper_large_v3_with_llama_3_8b_instruct,0.01831591655034519,0.03714982881570734,0.09876543209876543,0.14540692118393275,0.09515429104337297,0.11773910240019567,0.15611126487402763,0.038146268762641496,0.04754476156709803,0.0464432592211798,0.2904141703568638,0.33025751212260873,0.5142358733382134,0.4662862470067086,0.28367569330674514
+qwen_audio_chat,0.02246576376051609,0.04163277659031154,0.11645169375518152,0.30723956433545313,0.13316235845059654,0.38460383986837277,0.511809498898483,0.03995599872254356,0.45289842226555577,0.08434005911836524,0.5057046105756707,1.0992041596614108,1.3267786724597983,0.7411298037375774,0.46036235053411123

results/wer/cnasr.csv

@@ -1 +1,6 @@
 Model,aishell_asr_zh_test
+salmonn_7b,0.8527647443131199
+wavllm_fairseq,0.7054601967888183
+Qwen2-Audio-7B-Instruct,0.09317772366415236
+whisper_large_v3_with_llama_3_8b_instruct,
+qwen_audio_chat,0.06602522222882144