AI RESEARCH
Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation
arXiv CS.CL
•
ArXi:2604.04598v1 Announce Type: new Pashto is spoken by approximately 60--80M people but has no published benchmarks for multilingual automatic speech recognition (ASR) on any shared public test set. This paper reports the first reproducible multi-model evaluation on public Pashto data, covering zero-shot ASR, script-level failure, and cross-domain evaluation of fine-tuned models.