Paper proposes "Model as a Library" on-device speech architecture for low-resource African languages
The arXiv preprint (arXiv:2609.38574v1) introduces Model as a Library (MaaL), a system-design and position paper that packages small, community-enrolled speech models as versioned on-device dependencies to enable offline structured data collection. MaaL relies on closed‑vocabulary keyword spotting with vocabularies enrolled from a few example recordings by speakers at deployment and proposes transpiling existing closed‑vocabulary digital forms into MaaL schemas; the paper provides an analytical feasibility case and lists requirements for a working implementation.