Cohere Transcribe: Open-Source Speech Recognition | Cohere

This post details the release of Cohere Transcribe, an open-source Conformer-based encoder-decoder ASR model trained from scratch. It highlights its state-of-the-art accuracy (5.42% average WER) on the HuggingFace Open ASR Leaderboard, outperforming existing models. The post also discusses its performance across various datasets (AMI, Earnings 22, etc.) and human evaluations, emphasizing its robustness to real-world speech conditions. Furthermore, it presents throughput metrics (RTFx) demonstrating best-in-class serving efficiency for its model size cohort. The model supports 14 languages and is available via Hugging Face, API, and Model Vault.