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

Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

blog.mozilla.org

Post reply on HN
Print view View original

71–80 of 90 posts

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#71

Post by veli_joza »

StavrosK wrote: post #38

This is very timely, as today I was thinking of caving in and getting an Echo Dot so I can control my smart home devices by voice. I would love an open-hardware microphone array that I could use with a Pi or something similar, to write my own Alexa. Not only would I love this, I would store all my commands and send them to Mozilla to help with their speech recognition models. I don't want to be the guy who wishes som…

There are already some open source personal assistants, like Mycroft and Jasper. Integrating Mozilla's DeepSpeech into one of them would be fantastic.

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#73

Post by detaro »

olivier1664 wrote: post #72
richdougherty wrote: post #23

If you want to help them out you can visit https://voice.mozilla.org/ and record some sentences.

Do they have other languages than english?

It says "more languages coming soon" right on the page.

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#74

Post by beojan »

wslh wrote: post #14
yjftsjthsd-h wrote: post #11

Earlier quoted context omitted.

... it does what? Even if you disable the "Share Snippets" option?

There is no official statement of Google about this but there is a generic Android warning saying "This method can collect all of the text that you enter except passwords including personal data and credit card numbers.". I wonder why Google doesn't explicitly say what they are doing. I don't want to distribute FUD but this is a critical component.

That's because any keyboard could, theoretically, be a keylogger.

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#75

Post by charlysl »

sitkack wrote: post #59
muxator wrote: post #9

I am very grateful for this release from Mozilla, and more generally for the broad vision of their effort. As time passes, the quest for openness and freedom in software moves higher up in the stack. Thanks to the latest ~30 years of effort, we basically came to a point in which we have free OSes, basic infrastructure, building tools, end-user applications. In the last ~10 years we changed paradigm: autonomous deskto…

This period is only a phase while CNNs offer the best bang. As algorithms improve, the amount of data needed to train a model will drop 1000x making the big5's data hoards not worth nearly as much. In five years, the power will shift away from petabyte sized datasets.

My understanding is that data needed (aka data complexity) is independent of the algorithm. It depends only on model complexity (roughly # of free parameters in model). AFAIK this is a fundamental principle of ML that has been proven mathematically and which is inescapable.

https://en.m.wikipedia.org/wiki/VC_dimension

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#76

Post by 24gttghh »

TaylorAlexander wrote: post #55
muxator wrote: post #9

I am very grateful for this release from Mozilla, and more generally for the broad vision of their effort. As time passes, the quest for openness and freedom in software moves higher up in the stack. Thanks to the latest ~30 years of effort, we basically came to a point in which we have free OSes, basic infrastructure, building tools, end-user applications. In the last ~10 years we changed paradigm: autonomous deskto…

Thanks for the note about HW. In my field in robotics openness is not common (ROS being a major exception). I hold a rather uncommon view that a path to a more free society requires abundance of open source tools. In the software world we are getting closer, but the whole hardware world is still one big unmoving binary blob. I make open source robots and I’m hoping to help in that area. But we need open source machin…

I would think 3D printing, portable CNC machines[0], and custom PCB fabrications[1] are making headway into the openness of the HW space. I think that even before the tools, or maybe alongside of, there needs to be an abundance of cheap, clean energy to power the open source tools for the real revolution in manufacturing to take off.

[0]http://www.goliathcnc.com/

[1]https://oshpark.com/

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#77

Post by yorwba »

skykooler wrote: post #41
punchingwater wrote: post #33

Earlier quoted context omitted.

Don't forget Kaldi! https://github.com/kaldi-asr/kaldi

The problem with Kaldi is that it's virtually impossible to get a dictation model working with Kaldi unless you have a doctorate in speech recognition. There is no "I know basic programming, but little about speech recognition" documentation for Kaldi.

There's the "Kaldi for Dummies" tutorial [1], which helped me to the point of creating a speech recognition program that could distinguish digits in recordings of my voice. I guess that's the documentation you're looking for.

My personal problem with Kaldi is that I don't have enough RAM in my cheap laptop to work with any of the big models. When it started swapping just doing the preprocessing for one of the pretrained models [2], I kind of abandoned that project until I bother to get new hardware.

For that reason, I can't tell how good the pretrained models really are.

[1] http://kaldi-asr.org/doc/kaldi_for_dummies.html [2] http://kaldi-asr.org/models.html

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#78

Post by ekidd »

charlysl wrote: post #75
sitkack wrote: post #59

Earlier quoted context omitted.

This period is only a phase while CNNs offer the best bang. As algorithms improve, the amount of data needed to train a model will drop 1000x making the big5's data hoards not worth nearly as much. In five years, the power will shift away from petabyte sized datasets.

My understanding is that data needed (aka data complexity) is independent of the algorithm. It depends only on model complexity (roughly # of free parameters in model). AFAIK this is a fundamental principle of ML that has been proven mathematically and which is inescapable. https://en.m.wikipedia.org/wiki/VC_dimension

> AFAIK this is a fundamental principle of ML that has been proven mathematically and which is inescapable.

Well, the human brain manages to master several complex tasks using much smaller data sets than current machine learning algorithms. Natural language acquisition, for example, seems to require fewer than 10 million spoken words per year, and even academically successful 12-year-olds might be reading 1 to 4 million words per year. These are not exactly tiny data sets, but they don't require Google's scale to recreate, either.

Sure, the human genome probably "knows" what set of models to try when building the brain, which gives it an advantage. But I can't think of any reason why machine learning couldn't ultimately try similar techniques with similarly-sized data sets, and get competitive results.

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#79

Post by monsieurgaufre »

elaus wrote: post #53
monsieurgaufre wrote: post #31

I don't see why Mozilla would do this kind of things except to spread ressources. I know that it is an anecdote, but I don't know anyone who uses any kind of speech to text in part because they all suck if you don't speak english and even then..

Really? I know a ton of people who talk to their phones (Google Assistant, Siri, navigation apps, ...) or have something like Alexa in their homes and I don't live in an english speaking country.

I live in Montreal and don't know anyone who bought one or speak to their phone. Might be a cultural bias or just an anecdata as stated above.

Re: Initial Release of Mozilla’s Open Source Speech Recognition Model and Voice Data

#80

Post by charlysl »

ekidd wrote: post #78
charlysl wrote: post #75

Earlier quoted context omitted.

My understanding is that data needed (aka data complexity) is independent of the algorithm. It depends only on model complexity (roughly # of free parameters in model). AFAIK this is a fundamental principle of ML that has been proven mathematically and which is inescapable. https://en.m.wikipedia.org/wiki/VC_dimension

> AFAIK this is a fundamental principle of ML that has been proven mathematically and which is inescapable. Well, the human brain manages to master several complex tasks using much smaller data sets than current machine learning algorithms. Natural language acquisition, for example, seems to require fewer than 10 million spoken words per year, and even academically successful 12-year-olds might be reading 1 to 4 mill…

You are right.

I didn't phrase it correctly. What is algorithm independent is the theoretical performance bound for a given data complexity.

Sure, not all algorithms are the same, but the best performance that can theoretically be achieved with a given iid sample of a given size is algorithm independent.

So yes, a better algo can get same performance with less data, but limit stays the same.

Post reply on HN