Thomas Wolf(@Thom_Wolf)

Most people should probably update their priors on the state of open-source speech-to-speech. It's ...

6.4内容质量

TL;DR · AI 摘要

Thomas Wolf on X: "Most people should probably update their priors on the state of open-source speech-to-speech. It's ho...

核心要点

  • 主题聚焦：Most people should probably update their priors
  • 来源：Thomas Wolf(@Thom_Wolf)，建议结合原文判断细节。
  • AI 分析暂不可用，本条为保底评分与摘要。
#编程
打开原文

Thomas Wolf on X: "Most people should probably update their priors on the state of open-source speech-to-speech. It's honestly kind of mind-blowing. We teamed up with @cerebras to build a fully open-source realtime voice demo (models + code) to show what's possible today. Demo : https://t.co/vFpQ7jyoOK" / X

Thomas Wolf

@Thom_Wolf

Most people should probably update their priors on the state of open-source speech-to-speech. It's honestly kind of mind-blowing. We teamed up with

@

cerebras

to build a fully open-source realtime voice demo (models + code) to show what's possible today. Demo :

huggingface.co/spaces/smolage…

Blog:

huggingface.co/blog/cerebras-…

Go test it, fork it, tweak it, and impress your friends. video is raw, no cut, no speed-up, first take

00:00

11:31 PM · Jul 2, 2026

101.9K

Views

6

2

62

1

7

127

.

K

1.1K

1.6K

Read 62 replies