GigaAM Multilingual: Foundation Model for Underrepresented Languages

📅 2026-07-11
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the performance gap in multilingual automatic speech recognition for low-resource Central Asian languages—such as Kazakh, Kyrgyz, and Uzbek—caused by severe data scarcity. The authors propose a robust foundation model trained on 2 million hours of audio using a HuBERT-style objective to pretrain a Conformer encoder. To mitigate dominance by high-resource languages, they introduce a novel cluster-level data balancing strategy and a domain-aware fine-tuning sampling approach. Experimental results demonstrate that the proposed model significantly outperforms strong open-source baselines like Whisper Large v3, particularly on spontaneous speech, while maintaining efficient inference capabilities.
📝 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.
Problem

Research questions and friction points this paper is trying to address.

multilingual ASR
underrepresented languages
data scarcity
Central Asian languages
language imbalance
Innovation

Methods, ideas, or system contributions that make the work stand out.

data balancing
domain-aware sampling
Conformer encoder
HuBERT-style pretraining
underrepresented languages
💼 Related Jobs
No related jobs found.
A
Andrei Kuzmenko
SaluteDevices, Russia
A
Alexandr Maximenko
SaluteDevices, Russia
A
Aleksandr Kutsakov
SaluteDevices, Russia
G
Georgii Gospodinov
SaluteDevices, Russia
D
Dmitrii Bolotov
SaluteDevices, Russia
O
Oleg Kutuzov
SaluteDevices, Russia
P
Pavel Bogomolov
SaluteDevices, Russia
F
Fyodor Minkin
SaluteDevices, Russia