Live data from Hacker News

Show HN: JuliusJS – Speech recognition in JavaScript

github.com

51–55 of 55 posts

Re: Show HN: JuliusJS – Speech recognition in JavaScript

#51
post #47

Can you use any of the CMUSphinx compatible language models with this, or is there a tool to convert them to something Julius supports?

I believe that Julius offers their own tools for conversions like these, but the best place to consult would be the JuliusBook [1].

[1] http://julius.sourceforge.jp/juliusbook/en/

Re: Show HN: JuliusJS – Speech recognition in JavaScript

#52
post #46

Genuinely not sure if the demo is a joke or not. I said "hello" it said "DIAL OH OH". I said "Apple" it said "GET KENT". WTF?

In order to get a more comprehensive vocabulary/grammar, you need to substitute out the sample that it comes with. There are instructions in the README. For the demo, it just uses the sample grammar that voxforge provides, which is (as you can see) fairly limited.

Re: Show HN: JuliusJS – Speech recognition in JavaScript

#54
post #37

Earlier quoted context omitted.

Looks like they're just providing examples on serving the library on a webserver. It's all static JavaScript.

Right, it's all done on the client, so it is server agnostic.

Thanks for this lib!

Re: Show HN: JuliusJS – Speech recognition in JavaScript

#55
post #17

Earlier quoted context omitted.

Seeing cool things written in JavaScript makes you think that JavaScript is doomed?

Not to be that guy, but it wasn't written in JS it was transpiled from C to JS.

My point exactly. The end result being we are solidly entrenching Javascript into browsers, not the contrary. So instead of starting with a proper hammer for nails, we are slowly turning a screw driver into a blunt object which can neither screw nor hammer nails properly.
Post reply on HN