From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages

Summary

arXiv:2607.01502v1 Announce Type: new Abstract: Recent advances in automatic speech recognition (ASR) have explored different sequence models, including Conformer-based models and newer state space models such as Mamba. Although prior work has evaluated these architectures in multiple languages, their effectiveness in African languages remains underexplored. In this work, we evaluate Mamba for ASR on seven South African languages. In monolingual experiments, each model is trained on 50 hours of

SpinGraph analysis pending — check back after processing.

• Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
• Parameter Golf: What Really Works?
• Comparing Architectures for Supervised Political Scaling
• Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
• FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
• IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs