DiCoW DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper. BUT-FIT/DiCoW_v3_MLC Automatic Speech Recognition • 1.0B • Updated Sep 2 • 43 • 4 BUT-FIT/DiCoW_v1 Text Generation • 0.9B • Updated Sep 2 • 15 • 1 BUT-FIT/DiCoW_v2 0.9B • Updated Sep 2 • 5 • 2 BUT-FIT/DiCoW_v3_2 Automatic Speech Recognition • 1.0B • Updated Sep 2 • 1.26k • 6
BUT Czech LLMs BUT-FIT/csmpt7b Text Generation • 7B • Updated May 21 • 497 • 16 BUT-FIT/CSTinyLlama-1.2B Text Generation • 1B • Updated Dec 16, 2024 • 61 • 9 BUT-FIT/Czech-GPT-2-XL-133k Text Generation • 2B • Updated Nov 25, 2024 • 148 • 7 BUT-FIT/BUT-LCC Preview • Updated May 6, 2024 • 3 • 6
DiariZen DiariZen is a speaker diarization toolkit driven by AudioZen and Pyannote 3.1. BUT-FIT/diarizen-meeting-base Updated Jun 27 • 18 • 7 BUT-FIT/diarizen-wavlm-large-s80-md Voice Activity Detection • Updated Sep 2 • 574 • 23 BUT-FIT/diarizen-wavlm-large-s80-mlc Voice Activity Detection • Updated Sep 2 • 21 • 5 BUT-FIT/diarizen-wavlm-base-s80-md Updated Sep 2 • 274 • 1
DeCRED This collection showcases DeCRED (Decoder-Centric Regularisation in Encoder-Decoder) for ASR. BUT-FIT/DeCRED-base Automatic Speech Recognition • 0.2B • Updated Jan 7 • 2 BUT-FIT/DeCRED-small Automatic Speech Recognition • 39.8M • Updated Oct 22, 2024 • 1 BUT-FIT/ED-small Automatic Speech Recognition • 38.5M • Updated Oct 22, 2024 • 1 BUT-FIT/ED-base Automatic Speech Recognition • 0.2B • Updated Apr 23, 2024 • 1
DiCoW DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper. BUT-FIT/DiCoW_v3_MLC Automatic Speech Recognition • 1.0B • Updated Sep 2 • 43 • 4 BUT-FIT/DiCoW_v1 Text Generation • 0.9B • Updated Sep 2 • 15 • 1 BUT-FIT/DiCoW_v2 0.9B • Updated Sep 2 • 5 • 2 BUT-FIT/DiCoW_v3_2 Automatic Speech Recognition • 1.0B • Updated Sep 2 • 1.26k • 6
DiariZen DiariZen is a speaker diarization toolkit driven by AudioZen and Pyannote 3.1. BUT-FIT/diarizen-meeting-base Updated Jun 27 • 18 • 7 BUT-FIT/diarizen-wavlm-large-s80-md Voice Activity Detection • Updated Sep 2 • 574 • 23 BUT-FIT/diarizen-wavlm-large-s80-mlc Voice Activity Detection • Updated Sep 2 • 21 • 5 BUT-FIT/diarizen-wavlm-base-s80-md Updated Sep 2 • 274 • 1
BUT Czech LLMs BUT-FIT/csmpt7b Text Generation • 7B • Updated May 21 • 497 • 16 BUT-FIT/CSTinyLlama-1.2B Text Generation • 1B • Updated Dec 16, 2024 • 61 • 9 BUT-FIT/Czech-GPT-2-XL-133k Text Generation • 2B • Updated Nov 25, 2024 • 148 • 7 BUT-FIT/BUT-LCC Preview • Updated May 6, 2024 • 3 • 6
DeCRED This collection showcases DeCRED (Decoder-Centric Regularisation in Encoder-Decoder) for ASR. BUT-FIT/DeCRED-base Automatic Speech Recognition • 0.2B • Updated Jan 7 • 2 BUT-FIT/DeCRED-small Automatic Speech Recognition • 39.8M • Updated Oct 22, 2024 • 1 BUT-FIT/ED-small Automatic Speech Recognition • 38.5M • Updated Oct 22, 2024 • 1 BUT-FIT/ED-base Automatic Speech Recognition • 0.2B • Updated Apr 23, 2024 • 1