Voice control engine that runs fully in the browser using WebAssembly(picovoice.ai)
picovoice.ai
Voice control engine that runs fully in the browser using WebAssembly
https://picovoice.ai/
29 comments
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 extension without even hitting the button.
I thought I would need to look into compiling into web assembly myself, super impressed that this too has already been done.
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 extension without even hitting the button.
I thought I would need to look into compiling into web assembly myself, super impressed that this too has already been done.
Sounds like a great idea. Let us know if you face any problems integrating it. Happy to help. Cheers!
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.
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?
Otherwise, I am thinking it could be something related to the microphone?
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 weeks, and need to do a package upgrade to move up from 68.0, so this may not be interesting to anybody.
But in case someone sees this and wants to chase it down, let me know; debugging Chromium can be fun. Unfortunately Arch doesn't provide debug symbols for their builds :'( so that's a bit of a setback, but yeah.
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 weeks, and need to do a package upgrade to move up from 68.0, so this may not be interesting to anybody.
But in case someone sees this and wants to chase it down, let me know; debugging Chromium can be fun. Unfortunately Arch doesn't provide debug symbols for their builds :'( so that's a bit of a setback, but yeah.
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.
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.
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.
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.
Interesting tech, but on a very restricted demo it was wrong a huge number of times for me.
I'd recommend adding a note that the lamp itself will go red in response to "ok lamp", at least I think that's why it was doing that - it was a bit confusing and to see the first thing happen after saying "ok lamp, blue" having the picture of a lamp go red was not hugely encouraging initially. Perhaps add "listening for colour" or something.
I'd recommend adding a note that the lamp itself will go red in response to "ok lamp", at least I think that's why it was doing that - it was a bit confusing and to see the first thing happen after saying "ok lamp, blue" having the picture of a lamp go red was not hugely encouraging initially. Perhaps add "listening for colour" or something.
Oddly, all site text invisible in Chrome 55 (UC Browser) and FF 57. (text exists, but must be same as bg color, including all buttons)
The web demo doesn't work for me on Android.
Works for me on Android using Firefox.
Ah, it does for me too, though not reliably.
oulipo(3)
But their site says to email for licensing, which bodes poorly.
EDIT: License for "Porcupine" is Apache but with this:
THIS LICENSE APPLIES TO ASSETS IN THIS REPOSITORY INCLUDING DOCUMENTATION, SOURCE CODE, BINARIES, AND RESOURCE FILES EXCEPT FOR THE OPTIMIZER TOOL, ITS ASSOCIATED RESOURCE FILES, AND KEYWORD FILES GENERATED USING IT COLLECTIVELY LOCATED UNDER Porcupine/tools/optimizer. THE OPTIMIZER TOOL AND KEYWORDS FILES GENERATED USING IT ARE NOT GOVERNED BY THIS LICENSE. SPECIFICALLY THEIR USE IN COMMERCIAL PRODUCTS WITHOUT ACQUIRING A LICENSING AGREEMENT FROM PICOVOICE IS STRICTLY PROHIBITED.