Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Voice control engine that runs fully in the browser using WebAssembly

picovoice.ai

Post reply on HN
Print view View original

21–30 of 30 posts

Re: Voice control engine that runs fully in the browser using WebAssembly

#21

Post by kenarsa »

mikob wrote: post #12

Coincidentally I tried the python client just earlier today and was blown away. I never even had to record my voice, I just typed two words for the wake word and it was 95% accurate in picking them up even with heavy background noise. I am definitely going to integrate the wake word functionality into my Chrome extension that lets users control the browser via voice ( https://www.lipsurf.com ) so they can turn on the…

Sounds like a great idea. Let us know if you face any problems integrating it. Happy to help. Cheers!

Re: Voice control engine that runs fully in the browser using WebAssembly

#23

Post by mediocrejoker »

faissaloo wrote: post #22

Proprietary? No thanks, I'll just use Mozilla Deepspeech.

Serious question, how is that working so far?

I’d love to have Alexa/Google hone functionality but I’m not comfortable having a device made by those companies always listening in my home.

Really looking forward to when a product using Mozilla’s tech is available.

Re: Voice control engine that runs fully in the browser using WebAssembly

#24

Post by edoceo »

yjftsjthsd-h wrote: post #13
oulipo wrote: post #9

If you are interested in a voice engine which will be open-sourced soon and works on Raspberry Pi 3, iOS, Android, osX and Linux, you can take a look at what we are building at Snips https://snips.ai

> will be open-sourced soon Great! When that happens, I'll consider it.

They've been saying "soon" for over six months. Don't hold your breath.

Re: Voice control engine that runs fully in the browser using WebAssembly

#25

Post by rkagerer »

kenarsa wrote: post #19
joethebro wrote: post #7

Just to add my experience, the demo worked perfectly straight away (Chrome 70 on macOS). Really cool to see this tech, hope it's easy to integrate.

thanks a lot for the feedback :) Take a look at this standalone demo if you like https://github.com/Picovoice/Porcupine/tree/master/demo/js it should be a matter of tweaking a few parameters.

Web demo on your main page worked great for me at first, but stopped working after about half a dozen commands.

Re: Voice control engine that runs fully in the browser using WebAssembly

#26

Post by kenarsa »

rkagerer wrote: post #25
kenarsa wrote: post #19

Earlier quoted context omitted.

thanks a lot for the feedback :) Take a look at this standalone demo if you like https://github.com/Picovoice/Porcupine/tree/master/demo/js it should be a matter of tweaking a few parameters.

Web demo on your main page worked great for me at first, but stopped working after about half a dozen commands.

That's odd. If there are errors in the console. Please open an issue in the GitHub repo is possible: https://github.com/Picovoice/Porcupine

Otherwise, I am thinking it could be something related to the microphone?

Re: Voice control engine that runs fully in the browser using WebAssembly

#27

Post by exikyut »

yjftsjthsd-h wrote: post #14
exikyut wrote: post #5

Each of the >30 times I've hit F5 on this site in Chromium it causes a 100% reproducible, complete tab crash. The tab fully loads and appears properly for about... 100ms or so beforehand, so I'm pretty sure it's to do with some kind of wasm interaction. I have my microphone set to "ask before accessing" so I don't think the crash is to do with audio. FWIW, I've been experiencing periodic tab crashes for the past few…

Why are you not up to date? Chrom/ium has a stable extension API; it's not like it should break anything, and you're missing security and bug fixes.

Insufficient diskspace, to be honest (avg. 50-100MB free on /). Which is due to expensive medical issues that make it tricky for me to work.

Been a problem for a while - worked with just under 8MB free for two years on the 486 I used between 2003 and 2005.

The reason I'm doing my best to sit still until I can fix things properly is that buying small HDDs a) multiplies single points of failure beyond the many, many disks I have boxed up and hope still work, and b) increases the total capacity I'll need to _re-purchase_ when I can finally assemble a ZFS pool. Right now, I have enough 400MB and 4GB, 10GB, 60GB, etc HDDs that I need about 10TB (!!!!) of temporary capacity to sanely deduplicate everything.

I'll figure out a solution eventually.

Re: Voice control engine that runs fully in the browser using WebAssembly

#28

Post by mikob »

mediocrejoker wrote: post #23
faissaloo wrote: post #22

Proprietary? No thanks, I'll just use Mozilla Deepspeech.

Serious question, how is that working so far? I’d love to have Alexa/Google hone functionality but I’m not comfortable having a device made by those companies always listening in my home. Really looking forward to when a product using Mozilla’s tech is available.

You should look into MyCroft AI - it's an open source, privacy-conscious smart speaker company. You can buy one of their smart speakers or go the DIY route and install it on your own Raspberry Pi.

Re: Voice control engine that runs fully in the browser using WebAssembly

#29

Post by dang »

oulipo wrote: post #9

If you are interested in a voice engine which will be open-sourced soon and works on Raspberry Pi 3, iOS, Android, osX and Linux, you can take a look at what we are building at Snips https://snips.ai

This is pretty much (if not completely?) all you've been posting about to HN. It's one thing to occasionally share relevant work, but using HN for promotion crosses the line into spamming. Please stop.

Re: Voice control engine that runs fully in the browser using WebAssembly

#30

Post by faissaloo »

mediocrejoker wrote: post #23
faissaloo wrote: post #22

Proprietary? No thanks, I'll just use Mozilla Deepspeech.

Serious question, how is that working so far? I’d love to have Alexa/Google hone functionality but I’m not comfortable having a device made by those companies always listening in my home. Really looking forward to when a product using Mozilla’s tech is available.

It's more accurate than humans.
Post reply on HN