List your company
ResearchFormerly WizWand

Automatic Speech Recognition on SEAME Man (dev)

10.1MERWhisper-Largev3
6.87228.66150.4572.239Sep 29, 2025Nov 14, 2025Dec 31, 2025Feb 16, 2026Apr 3, 2026May 20, 2026Jul 6, 2026
Updated 3mo ago

Evaluation results

MethodLinks
Whisper-Largev3Real Duration (h)=100, TTS-R Duration (h)=1002026.0110.1
Whisper-large-v3 + ft full model#Train. Params.=1541.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0910.3
Whisper-Largev3Real Duration (h)=100, TTS-O Duration (h)=1002026.0111.1
Whisper-medium + ft full model#Train. Params.=762.3 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0911.5
Whisper-Largev3Real Duration (h)=1002026.0112.1
Whisper-Largev3TTS-R Duration (h)=2002026.0112.2
Whisper-Largev3TTS-O Duration (h)=1002026.0112.5
Subsequent Iterative, M2Iteration=22026.0712.88
Whisper-small + ft full model + w/ SPT*#Train. Params.=240.7 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.1
Whisper-small + ft full model#Train. Params.=240.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.2
Whisper-small + ft full model + w/ FA-LID-UB#Train. Params.=240.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.2
Whisper-small + ft full model + w/ FA-LID-LB#Train. Params.=240.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.3
Whisper-small + ft full model + w/ LAL#Train. Params.=240.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.3
First Iterative, M1Iteration=12026.0713.39
Whisper-small + adapt. w/ LoRA#Train. Params.=4.4 M, pre-training (pt)=true, Tuning=adaptation tuning2025.0913.5
Whisper-small + ft full model + w/ CTC-LID#Train. Params.=240.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0913.7
Whisper-small + adapt. w/ Bi-LoRA#Train. Params.=4.4 M, pre-training (pt)=true, Tuning=adaptation tuning2025.0913.8
Whisper-small + ft encoder-only#Train. Params.=87.0 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0914.6
Conformer + WavLM-large#Train. Params.=48.3 M, pre-training (pt)=true2025.0915.2
Conformer + XLS-R-0.3B#Train. Params.=48.3 M, pre-training (pt)=true2025.0915.3
Conformer + LLM GER#Train. Params.=48.3 M, pre-training (pt)=false2025.0915.7
E-Branchformer + CAMEL#Train. Params.=55.3 M, pre-training (pt)=false2025.0916.1
Conformer + LPB#Train. Params.=79.9 M, pre-training (pt)=false2025.0916.3
Conformer + ILB#Train. Params.=79.9 M, pre-training (pt)=false2025.0916.4
Conformer + LAL#Train. Params.=48.3 M, pre-training (pt)=false2025.0916.4
Branchformer#Train. Params.=39.0 M, pre-training (pt)=false2025.0916.4
E-Branchformer#Train. Params.=39.9 M, pre-training (pt)=false2025.0916.4
Conformer#Train. Params.=48.3 M, pre-training (pt)=false2025.0916.6
ConExtBiMamba*#Train. Params.=54.6 M, pre-training (pt)=false2025.0916.6
Whisper-small + ft decoder-only#Train. Params.=153.6 M, pre-training (pt)=true, Tuning=full-parameter fine-tuning2025.0917.4
Whisper-Largev3TTS-R Duration (h)=1002026.0117.7
Transformer#Train. Params.=29.8 M, pre-training (pt)=false2025.0917.7
Baseline2026.0719.23
Initial bilingual, M0Iteration=02026.0761.09
Whisper-large-v3pre-training (pt)=true2025.0973.5
Private model2026.0785.31
Whisper-mediumpre-training (pt)=true2025.0987.1
Whisper-smallpre-training (pt)=true2025.0990.8