Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

There are tons of open source STT models, what makes whisper so valuable? I especially don't get it on mobile, where the native STT built into the OS is now real-time and includes punctuation (at least for iOS). I love the open-source approach to the model, but it didn't strike me as particularly better than other open-source or built-in models.


In my limited testing, I've found Whisper to be much better (accuracy-wise) than other STT models.


For some reason, I recalled Whisper to be on-par or slightly worse than the other open source ones, but much better across languages. I appear to be wrong.


Just curious on What open source ones did you compare them with ? do you mean WER was high or ?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: