DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper.
AI & ML interests
None defined yet.
Recent Activity
DiariZen is a speaker diarization toolkit driven by AudioZen and Pyannote 3.1.
This collection showcases DeCRED (Decoder-Centric Regularisation in Encoder-Decoder) for ASR.
-
BUT-FIT/DeCRED-base
Automatic Speech Recognition • 0.2B • Updated • 34 -
BUT-FIT/DeCRED-small
Automatic Speech Recognition • 39.8M • Updated • 5 • 1 -
BUT-FIT/ED-small
Automatic Speech Recognition • 38.5M • Updated • 18 -
BUT-FIT/ED-base
Automatic Speech Recognition • 0.2B • Updated • 5
DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper.
DiariZen is a speaker diarization toolkit driven by AudioZen and Pyannote 3.1.
This collection showcases DeCRED (Decoder-Centric Regularisation in Encoder-Decoder) for ASR.
-
BUT-FIT/DeCRED-base
Automatic Speech Recognition • 0.2B • Updated • 34 -
BUT-FIT/DeCRED-small
Automatic Speech Recognition • 39.8M • Updated • 5 • 1 -
BUT-FIT/ED-small
Automatic Speech Recognition • 38.5M • Updated • 18 -
BUT-FIT/ED-base
Automatic Speech Recognition • 0.2B • Updated • 5