SE-DiCoW

Home/Models/BUT-FIT/SE-DiCoW

BUT-FIT/SE-DiCoW

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: —
provider: BUT-FIT
license: apache-2.0
language: —
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,131
likes: 8
created: —
last modified: 2026-01-26T18:25:36+00:00 (2026)
huggingface: https://huggingface.co/BUT-FIT/SE-DiCoW
tags: transformerssafetensorsDiCoWautomatic-speech-recognitionspeechwhispermultilingualspeaker-diarizationmeeting-transcriptiontarget-speaker-asrSE-DiCoWBUT-FITcustom_codedataset:microsoft/NOTSOFARdataset:edinburghcstr/amidataset:LibriSpeechMixdataset:LibriMixlicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
WER AMI	speech-asr	21.4	AMI (SDM)	medium	`\| AMI (SDM) \| 21.4% \| 18.5% \|`
WER LibriSpeech	speech-asr	17.9	LibriSpeechMix (2)	medium	`\| LibriSpeechMix (2) \| 17.9% \| 3.1% \|`

none scraped.