Alexander Polok

Lakoc's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 14 hours ago

BUT-FIT/DiCoW_v3_3_large

Automatic Speech Recognition • 2B • Updated about 13 hours ago • 1

liked a Space about 14 hours ago

Running on CPU Upgrade

Agents

11

FFASR Leaderboard

🎙

11

Far-Field ASR — clean / noisy / reverberant benchmark

published a model about 14 hours ago

BUT-FIT/DiCoW_v3_3_large

Automatic Speech Recognition • 2B • Updated about 13 hours ago • 1

liked a dataset 5 days ago

popcornell/NSF-QA

Viewer • Updated 5 days ago • 50.6k • 1.97k • 1

liked a model about 2 months ago

nvidia/parakeet-unified-en-0.6b

Automatic Speech Recognition • Updated about 18 hours ago • 743 • 51

updated a bucket 2 months ago

BUT-FIT/EMMA_leaderboard-storage

25.5 MB

published a bucket 2 months ago

BUT-FIT/EMMA_leaderboard-storage

25.5 MB

updated a Space 2 months ago

Running

Agents

14

EMMA MT-ASR benchmark

📊

14

Submit model results and view task leaderboards

New activity in BUT-FIT/DiCoW_v3_2 4 months ago

Original SE_DiCoW model missing from huggingface

1

#1 opened 4 months ago by

taavi223

updated a model 4 months ago

BUT-FIT/SE_DiCoW

Automatic Speech Recognition • 1B • Updated Feb 18 • 68 • 5

liked a Space 4 months ago

Configuration error

Agents

10

OWSM V4 Demo

🌍

10

This is a demo for OWSM-V4 CTC and medium model.

New activity in BUT-FIT/DiCoW_v3_3 4 months ago

Link model to SE-DiCoW paper and update metadata

1

#1 opened 4 months ago by

nielsr

submitted a paper to Daily Papers 4 months ago

SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper

Paper • 2601.19194 • Published Jan 27 • 3

New activity in microsoft/VibeVoice-ASR 4 months ago

seems that the model could not support overlapped speech recognition?

👍 3

7

#5 opened 5 months ago by

scutrandom

updated a model 4 months ago

BUT-FIT/SE-DiCoW

Automatic Speech Recognition • 1B • Updated Jan 26 • 2.02k • 6

updated a collection 4 months ago

DiCoW

Collection

DiCoW (Diarization-Conditioned Whisper) is a collection of speaker-aware ASR models developed by BUT-FIT, extending OpenAI’s Whisper. • 8 items • Updated Jan 26 • 2

published a model 4 months ago

BUT-FIT/SE-DiCoW

Automatic Speech Recognition • 1B • Updated Jan 26 • 2.02k • 6

updated a model 5 months ago

BUT-FIT/DiCoW_v3_3

Automatic Speech Recognition • 0.9B • Updated Jan 30 • 1.39k • 2

published a model 5 months ago

BUT-FIT/DiCoW_v3_3

Automatic Speech Recognition • 0.9B • Updated Jan 30 • 1.39k • 2