News for hackers. Stuff that matters.

A comment on GitHub is planning Voice to Code. Parent comment

Re:GitHub is planning Voice to Code by danielbln on Thursday November 10, 2022 @06:42AM (#33545075)
Speech to text is now amazing: https://huggingface.co/spaces/openai/whisper
[ Parent | on HN ]
Re:GitHub is planning Voice to Code by Semaphor on Thursday November 10, 2022 @07:16AM (#33545340)
It got "Theresa's and Aidsdorm" for "Turisas and Alestorm". Surprisingly, it got pretty close with the German band Schandmaul (something Alexa recognizes 100% of the time as Sean Paul), transcribing to "Schandmauel or Schandmöhrl".

But yeah, that is pretty close to amazing.

I kinda forgot about it after seeing that the Rhasspy community experimented with it, and it had issues with short utterances and a slow startup time.

[ Parent | on HN ]