The Open ASR Leaderboard Adds Its First Global South Language
Source
huggingface.co
Date
Why it matters
Hindi and Indian English now have held-out ASR splits with speaker metadata attached, so you can test how a speech model fails by region, age, device and accent instead of trusting one averaged error rate.
articleIntroducing the FFASR Leaderboard: Benchmarking ASR in the Real Worldhuggingface.co
articleSelecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 ModelsParishruthi Ganesh, Gerry Dozier, Cheryl Seals
articleMeasuring benchmark optimization in speech recognitionhuggingface.co