ElevenLabs发布Scribe v3语音转文字模型
AI 总结
ElevenLabs推出Scribe v3和Scribe v3 Live,并称其为该公司迄今最准确的语音转文字模型。公司表示,这些模型面向极端背景噪声、句末停顿和多人会议等场景。另一份所给报告称,模型的错误减少27%,并覆盖90多种语言,但未提供独立验证、基准、错误指标、测试集或测试方法。
深度见解
此次发布聚焦嘈杂音频和繁忙会议等高难度转写场景。所报告的准确率、错误减少比例和语言覆盖范围在现有证据中尚未得到独立验证。
Introducing Scribe v3 and Scribe v3 Live: our most accurate Speech to Text models yet.
Built for real-world audio, Scribe excels in situations with extreme background noise, knows pauses from the end of sentences, and keeps track of who said what in a busy meeting. https://x.com/ElevenLabs/status/2120217467100541396/video/1