Cohere 发布开源 ASR 模型 Transcribe，刷新语音识别准确率纪录
原标题：Cohere is announcing Transcribe, a state-of-the-art automatic speech recognition (ASR) model that is open source and available today for download.
AI 摘要
Cohere 发布了开源自动语音识别模型 Transcribe，基于 Conformer 架构，支持 14 种语言，在 HuggingFace Open ASR 排行榜上以 5.42% 的平均词错误率排名第一，超越 Whisper Large v3 等模型。该模型注重生产就绪性，提供高效推理和多种部署方式，并计划与 Cohere 的代理编排平台 North 集成。
正文节选
Cohere is announcing Transcribe, a state-of-the-art automatic speech recognition (ASR) model that is open source and available today for download. Speech is rapidly becoming a core modality for AI-enabled workloads and automations — from meeting transcription and speech analytics to real-time customer support agents. Our objective was straightforward: push the frontier of dedicated ASR model accuracy under practical conditions. The model was trained from scratch with a deliberate focus on minimi