Skip to content
Preprint

MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond

Jul 2026 · 0 citations · 44 references
Computer Science Engineering

TL;DR

MEUSLI is introduced, the first open-science multilingual projector family that links a Whisper encoder with open-source multilingual LLMs, enabling fully open-source end-to-end ASR in 28 European languages.

Abstract

Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for tasks like ASR and spoken question answering. Existing systems, however, typically only support a few languages and are often limited to English. We introduce MEUSLI, the first open-science multilingual projector family that links a Whisper encoder with open-source multilingual LLMs, enabling fully open-source end-to-end ASR in 28 European languages. MEUSLI extends prior monolingual pipelines, delivering strong results across high- and low-resource languages. Using proper continual leaning techniques, MEUSLI can be easily extended to other languages not seen in training. We further demonstrate that the MEUSLI projector can be leveraged beyond ASR, enabling multilingual speech translation and topic identification with only a few hours of task specific supervision per language. Overall, MEUSLI provides a solid foundation for multilingual speech understanding tasks, supporting scalable and inclu- sive open-source SpeechLLM

View source

Similar papers

Preprint Jul 2026

Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models

The results suggest that competitive MLLM can emerge from alignment alone, reducing multimodal extension to a lightweight projector-training problem that generalizes across modalities and adapts rapidly to each new LLM release.

Xuanru Zhou, Yiwen Shao, Jiahong Li et al. · 1 citation
Preprint Jul 2026

DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages

We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, for one family, three-step) learning-rate-annealed fine-tuning procedure that first adapts a shared multilingual model at a high learning rate and then anneals it to recover, and in several cases surpass, strong monolingual baselines. We further describe a lightweight language-conditioning mechanism that injects a one-hot language identity as a sequence of prefix frames prepended to the acoustic features, allowing a single multilingual checkpoint to be steered to a target language at inference. Across the five multilingual families the annealed models reach average word error rates (WER) of 10-13%, closing most of the gap to monolingual models while covering many languages in a single checkpoint. All models are released on the Hugging Face KhayaAI organisation under the Apache-2.0 license (attribution only) so that others may fine-tune them freely, including for commercial use. We provide a conservative estimate that the languages covered are spoken by on the order of one hundred million first-language speakers, and by substantially more when second-language use is included.

P. Azunre, N. Ibrahim, Joel Budu et al. · 0 citations
Preprint Aug 2026

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

Empirical analyses show that MoSE improves high-, medium-, and low-resource languages simultaneously, with the largest gains on low-resource speech, thereby breaking the curse of multilinguality without compromising high-resource performance.

Yexing Du, Kaiyuan Liu, Youcheng Pan et al. · 0 citations
Preprint Aug 2026

Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation

The results show that multilingual transfer is the dominant factor in extremely low-resource Bantu translation while eliminating the need for heuristic proxy selection, and all systems fail to preserve tonal diacritics, highlighting an open challenge.

Samiratu Ntohsi, Neza David Tuyishimire, Anesu Kafesu et al. · 0 citations
Preprint Jul 2026

GigaAM Multilingual: Foundation Model for Underrepresented Languages

This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages by presenting GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective, and introduces a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance.

Andrei Kuzmenko, A. Maximenko, Aleksandr Kutsakov et al. · 0 citations
Preprint Jul 2026

MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition

Results demonstrate that MoLGE consistently outperforms dense multilingual baselines with a minimal increase in trainable parameters, and suggest that structured language specialization provides an effective pathway for massively scaling language coverage of multilingual ASR.

Sangmin Lee, Woo-Jin Chung, Woongjib Choi et al. · 0 citations