Group Relative Policy Optimisation (GRPO) is applied to a non‑LLM encoder‑decoder ASR model, Whisper‑large‑v3, to improve multilingual speech recognition across 51 African languages. The method mitigates exposure bias from teacher forcing, especially benefiting low‑resource and noisy audio scenarios. The resulting model, SunflowerASR, sets new macro‑averaged WER records on AfriVox‑v2 (0.227) and SimbaBench (0.372).
arXiv:2508. 05149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks.
The paper introduces WaxalNet, a benchmark and adaptation study for spontaneous speech recognition across 19 African languages using the WAXAL corpus. It evaluates zero‑shot and fine‑tuned performance of several multilingual foundation models (Whisper, MMS, Omnilingual ASR, SeamlessM4T‑v2), showing that fine‑tuning can substantially reduce word error rates and that LLM decoders generally outperform CTC decoders when the encoder is shared. The authors also demonstrate that a single multilingual model can serve all languages with only a modest WER penalty and provide a native‑speaker audit of failure modes.
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.
arXiv:2609.23825v1 Announce Type: new Abstract: We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM archite...
arXiv:2510. 20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications.
arXiv:2609.09554v1 Announce Type: new Abstract: We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages. L...
arXiv:2603.29217v3 Announce Type: replace-cross Abstract: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing...
arXiv:2609.38106v1 Announce Type: cross Abstract: Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggre...
arXiv:2609.15758v1 Announce Type: new Abstract: Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed...
arXiv:2605. 13087v2 Announce Type: replace-cross Abstract: Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance.
arXiv:2601. 18904v3 Announce Type: replace-cross Abstract: Generative AI for speech and audio is increasingly expected to serve users across languages, cultures, and communities, yet current auditory Large Language Models (LLMs) are still largely trained and evaluated on high-resource data.
arXiv:2607. 04814v1 Announce Type: cross Abstract: Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the prohibitive demands of data collection at scale.