Speech-to-Text Client-Side?

2 点作者 novantadue将近 3 年前

Is there any way to do conversational speech-to-text in the browser/with mobile GPUs? Or do we need to still choose a cloud provider?

2 条评论

zcw100将近 3 年前

Give Vosk-Browser a try <a href="https://github.com/ccoreilly/vosk-browser" rel="nofollow">https://github.com/ccoreilly/vosk-browser</a><p>You can also try kaldi-wasm but it hasn't been worked on for a while <a href="https://gitlab.inria.fr/kaldi.web/kaldi-wasm" rel="nofollow">https://gitlab.inria.fr/kaldi.web/kaldi-wasm</a>

Dasky将近 3 年前

I think speechly is working on that: <a href="https://www.ycombinator.com/companies/speechly" rel="nofollow">https://www.ycombinator.com/companies/speechly</a>