跳到正文
K = 0.731订阅
教程

实时场景中的转录是什么样的？🎙我们在 AI Engineer Paris 使用 Voxtral 3 Transcribe，实时记录了所有主舞台演讲。我们通过上下文偏置提高了准确率，将会议议程中的演讲者姓名和技术术语提供给模型。相同的技术也可用于您自己的活动和应用。

Mistral AI · X· @MistralAI·· 4 天前

1359 次浏览 · 10 赞 · 1 转发 （收录时）

在 X 查看原推
原文
谁
Mistral AI
引文
We boosted accuracy with context biasing, feeding the model speaker names and technical terms from the conference agenda.

发生了什么

实时场景中的转录是什么样的？ 🎙我们在 AI Engineer Paris 使用 Voxtral 3 Transcribe，实时记录了所有主舞台演讲。我们通过上下文偏置提高了准确率，将会议议程中的演讲者姓名和技术术语提供给模型。 相同的技术也可用于您自己的活动和应用。

接下来读什么

查看这件事的完整进展Mistral AI Uses Context Biasing for Live Conference Transcription

2 篇报道

    正文 · 中文版本尚未就绪（原文）

    What does real-time transcription look like in a live setting?

    🎙We used Voxtral 3 Transcribe at AI Engineer Paris to capture every main-stage talk in real time. We boosted accuracy with context biasing, feeding the model speaker names and technical terms from the conference agenda.

    The same tech is available for your own events and apps.

    这件事到目前为止

    Mistral AI used Voxtral 3 Transcribe to capture every main-stage talk at AI Engineer Paris in real time, feeding speaker names and technical terms from the conference agenda to the model as context. The company said this context biasing improved transcription accuracy. Mistral said the same technology is available for other events and apps.

    语音与音频教程实践