Downloads · 30 days
0
KSE-RESEARCH-Group/omniASR-CTC-300M-uk-hutsul-tuned
omniASR-CTC-300M-uk-hutsul-tuned is a automatic speech recognition model from KSE-RESEARCH-Group. Use it when you need speech turned into text.
Fine-tuned omniASR CTC 300M on Ukrainian hutsul dialects dataset. Best checkpoint at step 60000 with
Downloads · 30 days
0
Access
Public
Updated Mar 5, 2026
Repo size
3.9 GB
Likes
0
Public
Click a slice to open those files.
.pt3.9 GB · 100%
From the Hugging Face model README
Fine-tuned omniASR CTC 300M on Ukrainian hutsul dialects dataset. Best checkpoint at step 60000 with
WER: 28.99%
CER: 11.72%