Our open-source speech-to-text model has secured the top spot for English language accuracy on HuggingFace’s Open ASR model leaderboard, achieving an impressive word error rate of just 5.42% and validated by human evaluation. We've also successfully achieved one of the strongest accuracy-speed ratios among speech models of a comparable size.

→ View original post on X — @cohere, 2026-03-26 13:27 UTC