Cohere 发布开源语音识别模型 Cohere Transcribe
先了解这件事
Cohere 于 2026 年 3 月 26 日通过官方博客宣布推出开源自动语音识别（ASR）模型 Cohere Transcribe，称其为开源语音识别领域的新 state-of-the-art，并开放下载。Cohere 表示语音正迅速成为 AI 工作负载的核心模态。目前公开信息仅来自这一篇一手博客，尚无第三方评测、社区反馈或后续版本更新等可核验进展。
根据公开报道整理 · 2 小时前更新
报道时间线
沿着报道，了解事件的不同侧面。
- Cohere Blog官方一手Introducing Cohere Transcribe: a new state-of-the-art in open-source speech recognitionMar 26, 20263 min read
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 delib
本事件热度走势
当前热度 9·可比范围峰值 10（10月18日 09:00）·近 24 小时可比范围变化 –
趋势仅比较持续完整观测到的相同主体，范围可能小于当前热度统计。移动指针或点击图表查看每小时热度；键盘可用左右方向键切换。