List your company
ResearchFormerly WizWand

Speech Recognition on EMNS

4.9WERTLE+TTS+ILME
1.71623.20844.766.192Sep 12, 2025
Updated 5mo ago

Evaluation results

MethodLinks
TLE+TTS+ILMEIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.094.9
TTS+ILMEIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.095.2
TLE+TTSIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.095.3
TLE+TTS+ILMEIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.095.5
TTSIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.095.6
TLE+ILMEIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.095.7
TTS+ILMEIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.095.8
TTSIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.096
TLE+TTSIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.096.1
TLE+TTS+SFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.096.1
TLE+TTS+ILMEIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.096.3
TLE+TTS+SFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.096.6
TLE+TTS+SFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.096.6
TTS+ILMEIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.096.8
TLE+TTSIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.097.2
TTS+SFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.097.4
TLE+ILMEIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.097.7
TTS+SFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.098.1
TLEIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.098.3
TLE+TTSIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.098.7
NoneIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.098.7
TTS+SFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.098.8
TLEIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.099.3
TLEIn-Domain=LS, Model=Canary-180M-flash2025.099.4
TLEIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.099.5
ILMEIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.099.6
SFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0910.1
StandardIn-Domain=CV, Model=Canary-180M-flash2025.0910.4
TLEIn-Domain=CV, Model=Canary-180M-flash2025.0910.6
TTSIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0910.8
TLEIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0911.3
TLE+SFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0911.7
TTSIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0911.8
NoneIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0911.8
ILMEIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0912.1
TLE+SFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0912.4
TLE+TTS+DFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0914
TLE+TTS+DFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0914.3
TTS+DFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0914.5
NoneIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0914.6
SFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0915.2
TLE+DFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0916.1
TLE+ILMEIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0916.6
NoneIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0916.7
TLE+DFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0916.8
TLE+SFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0916.9
DFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0917
TLE+TTS+ILMEIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0917
ILMEIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0917.2
SFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0917.6
TTS+DFIn-Domain Dataset=CommonVoice, Backbone=Whisper-Large2025.0918.3
TLE+TTS+DFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0918.9
TTS+DFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0919
DFIn-Domain Dataset=CommonVoice, Model Architecture=Whisper-Medium2025.0919.7
StandardIn-Domain=LS, Model=Canary-180M-flash2025.0920.5
TLE+DFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0921.4
DFIn-Domain Dataset=LibriSpeech, Model Architecture=Whisper-Medium2025.0921.8
TTS+ILMEIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0923.1
TLE+TTS+DFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0924.3
TLE+ILMEIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0925.6
TLE+TTS+SFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0926.3
TLE+SFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0927.3
TTS+DFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0931.6
TLE+DFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0932.1
ILMEIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0934.3
TTS+SFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0941.6
DFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0972.2
SFIn-Domain Dataset=LibriSpeech, Backbone=Whisper-Large2025.0984.5