{"ID":6536469,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T15:38:47.698199434Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10371","arxiv_id":"2607.10371","title":"GigaAM Multilingual: Foundation Model for Underrepresented Languages","abstract":"Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective. Crucially, we introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance. In controlled comparisons, our approach outperforms strong open pretrained encoders (Whisper Large v3, Omnilingual-1B) on target languages, achieving significant gains on spontaneous speech while maintaining efficiency. We release the foundation encoder and ASR model, offering a proven recipe for effective multilingual adaptation under realistic data imbalance.","short_abstract":"Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM Multilingual,...","url_abs":"https://arxiv.org/abs/2607.10371","url_pdf":"https://arxiv.org/pdf/2607.10371v1","authors":"[\"Andrei Kuzmenko\",\"Alexandr Maximenko\",\"Aleksandr Kutsakov\",\"Georgii Gospodinov\",\"Dmitrii Bolotov\",\"Oleg Kutuzov\",\"Pavel Bogomolov\",\"Fyodor Minkin\"]","published":"2026-07-11T15:48:03Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.CL\"]","methods":"[]","has_code":false}