Voice2json: Offline speech and intent recognition on Linux • Hacker News Board

Re: Voice2json: Offline speech and intent recognition on Linux

#11

Post by jfarina » Fri, May 21, 2021, 5:37 PM UTC

sodality2 wrote: post #6

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Mozilla CommonVoice is definitely trying. I always do a few validations and a few clips if I have a few minutes to spare, and I recommend everyone does. They need volunteers to validate and upload speech clips to create a dataset. https://commonvoice.mozilla.org/en

I wonder if they use movies and tv; recordings where the script is already available.

Re: Voice2json: Offline speech and intent recognition on Linux

#12

Post by londons_explore » Fri, May 21, 2021, 5:39 PM UTC

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Speech recognition algorithms today require lots of data, lots of training computation, and a decent design.

Decent designs are in published papers all over the place, so thats a solved issue.

Lots of compute requires lots of $$$, which isn't opensource-friendly.

Lots of data also isn't really opensource friendly.

Sadly this is a niche that the opensource business model doesn't really fit.

Re: Voice2json: Offline speech and intent recognition on Linux

#13

Post by marcodiego » Fri, May 21, 2021, 5:39 PM UTC

londons_explore wrote: post #10

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Good speech recognition generally requites massive mountains of training data, both labelled and unlabelled. Massive mountains of data tends to be incompatible with opensource projects. Even Mozilla collecting user statistics is pretty controversial. Imagine someone like Mozilla trying to collect hundreds of voice clips from each of tens of millions of users!!

Really complicated question, but considering the free world got wikipedia and openstreetmaps, I'd bet we'll find a way.

Re: Voice2json: Offline speech and intent recognition on Linux

#14

Post by marcodiego » Fri, May 21, 2021, 5:41 PM UTC

londons_explore wrote: post #12

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Speech recognition algorithms today require lots of data, lots of training computation, and a decent design. Decent designs are in published papers all over the place, so thats a solved issue. Lots of compute requires lots of $$$, which isn't opensource-friendly. Lots of data also isn't really opensource friendly. Sadly this is a niche that the opensource business model doesn't really fit.

People would probably say the same about wikipedia 20 years ago. People said similar things about gnu, gcc and linux 30 years ago.

Re: Voice2json: Offline speech and intent recognition on Linux

#15

Post by wcarss » Fri, May 21, 2021, 5:41 PM UTC

sodality2 wrote: post #6

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Mozilla CommonVoice is definitely trying. I always do a few validations and a few clips if I have a few minutes to spare, and I recommend everyone does. They need volunteers to validate and upload speech clips to create a dataset. https://commonvoice.mozilla.org/en

I've used the deepspeech project a fair amount and it is good. It's not perfect, certainly, and it honestly isn't good enough yet for an accurate transcription in my mind, but it's good. Easy to work with, pretty good results, and all the right kinds of free.

Thanks for taking time to contribute!

Re: Voice2json: Offline speech and intent recognition on Linux

#16

Post by offtop5 » Fri, May 21, 2021, 5:41 PM UTC

Fantastic.

Might use this with a Raspberry pi to set up some projects around the house. Is it possible to buy higher quality voice data ?

Re: Voice2json: Offline speech and intent recognition on Linux

#17

Post by twobitshifter » Fri, May 21, 2021, 5:42 PM UTC

hirundo wrote: post #7

I wonder if it would be possible to map vim keybindings to sounds and effectively drive the editor with the mouth when the hands are otherwise occupied. It might be possible to use sounds that compose into pronounceable words with minimal syllables for combinations. What would vim bindings look like as a concise command language suited to human vocalization? E.g. maybe "dine" maps to d$ and "chine" to c$. So as in ke…

https://youtu.be/8SkdfdXWYaI?t=600

this guy is already there: Slurp slap scratch buff yank

Re: Voice2json: Offline speech and intent recognition on Linux

#18

Post by sildur » Fri, May 21, 2021, 5:44 PM UTC

londons_explore wrote: post #12

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Speech recognition algorithms today require lots of data, lots of training computation, and a decent design. Decent designs are in published papers all over the place, so thats a solved issue. Lots of compute requires lots of $$$, which isn't opensource-friendly. Lots of data also isn't really opensource friendly. Sadly this is a niche that the opensource business model doesn't really fit.

> Lots of compute requires lots of $$$, which isn't opensource-friendly.

Not really, look up BOINC.

Re: Voice2json: Offline speech and intent recognition on Linux

#19

Post by wongarsu » Fri, May 21, 2021, 5:52 PM UTC

jfarina wrote: post #11

sodality2 wrote: post #6

Earlier quoted context omitted.

Mozilla CommonVoice is definitely trying. I always do a few validations and a few clips if I have a few minutes to spare, and I recommend everyone does. They need volunteers to validate and upload speech clips to create a dataset. https://commonvoice.mozilla.org/en

I wonder if they use movies and tv; recordings where the script is already available.

That's fine for training your own model, but I don't think you could distribute the training set. That seems like a clear copyright violation, against one of the groups that cares most about copyright.

Maybe you could convince a couple of indie creators or state-run programs to licence their audio? But I'm not sure if negotiating that is more efficient than just recording a bit more audio, or promoting the project to get more volunteers.

Re: Voice2json: Offline speech and intent recognition on Linux

#20

Post by posmonerd » Fri, May 21, 2021, 5:56 PM UTC

londons_explore wrote: post #10

marcodiego wrote: post #4

Good FLOSS speech recognition and TTS is badly needed. Such interaction should not be left to an oligoply with bad history of not respecting users freedoms and privacy.

Good speech recognition generally requites massive mountains of training data, both labelled and unlabelled. Massive mountains of data tends to be incompatible with opensource projects. Even Mozilla collecting user statistics is pretty controversial. Imagine someone like Mozilla trying to collect hundreds of voice clips from each of tens of millions of users!!

Not an expert on any of this, but wouldn’t already published content (public or proprietary) such as Youtube videos, audiobooks, tv interviews, movies, tv programs, radio programs, podcasts, etc. be useful and exempt from privacy concerns?

Do user collected clips have soemthing so special to the point that it’s critical to collect them?