# GigaAM Multilingual: Foundation Model for Underrepresented Languages

arXiv: https://arxiv.org/abs/2607.10371 · HTML: https://mlsanity.com/paper/2607.10371/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage](https://mlsanity.com/paper/2111.09344/) (2021)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [YODAS: Youtube-Oriented Dataset for Audio and Speech](https://mlsanity.com/paper/2406.00899/) (2024)
- [GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement](https://mlsanity.com/paper/2406.11546/) (2024)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning](https://mlsanity.com/paper/2506.00338/) (2025)
- [KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset](https://mlsanity.com/paper/2104.08459/) (2021)
- [On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models](https://mlsanity.com/paper/2406.09282/) (2024)
- [Golos: Russian Dataset for Speech Research](https://mlsanity.com/paper/2106.10161/) (2021)
- [A Toolbox for Construction and Analysis of Speech Datasets](https://mlsanity.com/paper/2104.04896/) (2021)
- [USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments](https://mlsanity.com/paper/2107.14419/) (2021)
- [The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties](https://mlsanity.com/paper/2509.07139/) (2025)
- [GigaAM: Efficient Self-Supervised Learner for Speech Recognition](https://mlsanity.com/paper/2506.01192/) (2025)

## Abstract (arXiv)

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.