Hugging Face has added a new benchmark, Benchmaxxer Repellant, to its Open ASR Leaderboard. The leaderboard ranks speech recognition models based on their performance on various benchmarks. By adding this new benchmark, Hugging Face aims to provide more comprehensive evaluations of these models. --- Why it matters: This matters because it allows researchers and developers to compare the performance of different speech recognition models in a more nuanced way, potentially leading to improvements in model accuracy and robustness. Source: https://huggingface.co/blog/open-asr-leaderboard-private-data