central-asian-languages

This paper introduces GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio with a HuBERT-style objective, addressing data scarcity for Central Asian languages (Kazakh, Kyrgyz, Uzbek). It employs cluster-level data balancing and domain-aware sampling to outperform strong baselines like Whisper Large v3 on target languages.