Mozilla Releases Open Source Speech Recognition Model, Massive Voice Dataset (mozilla.org) 58
Mozilla's VP of Technology Strategy, Sean White, writes:
I'm excited to announce the initial release of Mozilla's open source speech recognition model that has an accuracy approaching what humans can perceive when listening to the same recordings... There are only a few commercial quality speech recognition services available, dominated by a small number of large companies. This reduces user choice and available features for startups, researchers or even larger companies that want to speech-enable their products and services. This is why we started DeepSpeech as an open source project.
Together with a community of likeminded developers, companies and researchers, we have applied sophisticated machine learning techniques and a variety of innovations to build a speech-to-text engine that has a word error rate of just 6.5% on LibriSpeech's test-clean dataset. vIn our initial release today, we have included pre-built packages for Python, NodeJS and a command-line binary that developers can use right away to experiment with speech recognition.
The announcement also touts the release of nearly 400,000 recordings -- downloadable by anyone -- as the first offering from Project Common Voice, "the world's second largest publicly available voice dataset." It launched in July "to make it easy for people to donate their voices to a publicly available database, and in doing so build a voice dataset that everyone can use to train new voice-enabled applications." And while they've started with English-language recordings, "we are working hard to ensure that Common Voice will support voice donations in multiple languages beginning in the first half of 2018."
"We at Mozilla believe technology should be open and accessible to all, and that includes voice... As the web expands beyond the 2D page, into the myriad ways where we connect to the Internet through new means like VR, AR, Speech, and languages, we'll continue our mission to ensure the Internet is a global public resource, open and accessible to all."
Together with a community of likeminded developers, companies and researchers, we have applied sophisticated machine learning techniques and a variety of innovations to build a speech-to-text engine that has a word error rate of just 6.5% on LibriSpeech's test-clean dataset. vIn our initial release today, we have included pre-built packages for Python, NodeJS and a command-line binary that developers can use right away to experiment with speech recognition.
The announcement also touts the release of nearly 400,000 recordings -- downloadable by anyone -- as the first offering from Project Common Voice, "the world's second largest publicly available voice dataset." It launched in July "to make it easy for people to donate their voices to a publicly available database, and in doing so build a voice dataset that everyone can use to train new voice-enabled applications." And while they've started with English-language recordings, "we are working hard to ensure that Common Voice will support voice donations in multiple languages beginning in the first half of 2018."
"We at Mozilla believe technology should be open and accessible to all, and that includes voice... As the web expands beyond the 2D page, into the myriad ways where we connect to the Internet through new means like VR, AR, Speech, and languages, we'll continue our mission to ensure the Internet is a global public resource, open and accessible to all."
Why is Firefox CPU use and memory use unstable? (Score:2, Insightful)
Why does Firefox use so much memory when there are only a few tabs open? Why does Firefox increase memory use when it is not being viewed?
Re: (Score:2)
Are you new to FF or something? It's done that before there were bitmines.
Yes, Firefox has always been unstable. (Score:2)
Re: (Score:2)
1) It could be the fault of a Web site that you have open. A browser can't easily distinguish "valid" from "invalid" Web site resource usage.
2) It could be a Firefox bug, but if it is, it certainly doesn't happen for everyone or even most people. If it did, it would have been fixed already.
Firefox is unstable with many windows and tabs. (Score:2)
I need to do a LOT of research. I often open windows and tabs in Firefox and then need to think about what I've seen, so I leave the windows and tabs open.
Then I do other research. That often results in having many windows and tabs open. Soon Firefox begins grabbing CPU power and memory. Eventually the Windows 7 Ultimate OS becomes slow. Sometimes it appears that Firefox has made Windows unstable.
Pale Moon 64-bits [palemoon.org] seems more stable
Re:I'm not interested in giving Mozilla money (Score:4, Informative)
The vast majority of Mozilla's money is spent on Firefox.
You just made up "most of their money is spent on community projects" out of thin air, didn't you?
Re: (Score:2)
They have been neglecting the security aspect of their browser for 20+ years while continually throwing in new projects like this utilizing developers whose caliber of work would not qualify them for jobs in the professional sector.
20+ years? Really? Mozilla is only 19 years old. Firefox is only 15 years old.
Re: (Score:2)
I read it as "Incompetence in web browser security has been the rule since they were called Netscape."
Re: (Score:3)
Another example of just making stuff up.
Actually it's quite irksome to read trolling like this given I spent most of my long, paid employment at Mozilla fixing bugs, including security issues and worked with hundreds of dedicated colleagues also doing that.
Firefox's security record is not much different from other Web browsers, and better than some. And it's getting even better now that the latest Firefox releases have quite good content-process sandboxing.
1st thing that made me WANT to give them $ !!! (Score:5, Insightful)
If - and I don't yet know if this is the case, they don't actually seem to say - this represents a stand-alone, does-not-go-to-the-LAN-or-WAN speech-to-text system... with an error rate of 6.5% on English speech as claimed... then it's way more important than Yet Another Web Browser.
This is precisely the kind of thing projects like Mycroft [mycroft.ai] need to become not just another way to send your activity out on the net, which inherently decreases both reliability and security.
If indeed this is what this is, then the door opens for all manner of sophisticated home advances we can actually trust and depend on.
They claim around 1:1 [decode rate : normal speech rate] with a reasonably modern CPU/GPU. That needs considerable improvement. Reference quote from here: [mozilla.org]
That's a lot of computing power to hand off, particularly in a laptop. Using just the CPU, you'll be pegging it the whole time you're talking, and then some. For a decent desktop, it's at least doable, but it's still a very heavy compute load.
Though... saying "MacBook Pro" doesn't really tell us enough... I have a MacBook Pro that is a dual-core Intel machine... it's not what you'd call quick. There are a lot of different hardware configs that could be described by "MacBook Pro."
Seems like a pretty big deal to have to dedicate a server to the STT task (but then again, if I could get my STT tasks out from under the cloud... I'd probably do it. I have a spare 3 GHz 8-core hanging around, so...) but I think for general use, they have to do better. This isn't going to fly well on a Raspberry pi, for instance, it'll just get way behind.
Still. IMHO, this may be important. Very.
Re: (Score:2)
Just make it sound like Majel Barrett-Roddenberry and have it go "Working....kjunk kjunk kjunk kjunk... " while it works through the buffered speech data.
Re: (Score:2)
I don't think they've put much/any effort into optimizing the recognizer yet.
Innovation (Score:2)
Certainly this will be part of the browser.
Obviously, the Mozilla folks see that direct text input devices may not play a big role in our future, or indeed our present, and they don't want to use the Internet services of another browser maker (Apple, Google, Microsoft, Amazon) to enable non-text on their browser. This would be slower than local recognition and not under their control. Or yours.
It's really easy to stifle innovation by requiring an over-tight focus. Many companies fail by doing just this.
Re: (Score:2)
Thinks like this will make the browser better in the future! They have vision and want to be a leader in future tech solutions.
That future is not that far away, you have currently siri, alexa and friends growing up, you have mobile phones, where write is hard and speak is easier, you may have automatic voice translations, where the first step is of course, voice recognition.
When MS, Apple, Google release their browsers with build in screen reads, automatic translation and speech recognition, firefox also ne
This changes the game entirely! (Score:2, Funny)
I had a problem with voice assistants because it was not being done inside my circle of trust (but closer to a sworn enemy).
If I can run this on my home server, it will completely change the game.
I could now actually implement Star-Trek-style home automation, if I needed it.
"Computer, switch mood to" evening'." (campfire color scheme lights, shutters down, adjust screen warmth, play some relaxing music, mix me some nice drink [I'm building a drink mixer] and connect me to a tight slut)
Re: (Score:3)
My first question, is 6.5% error rate considered good? Surely it has uses, but it seems to be good for "things that aren't important enough to write down right now, but I want a half-ass transcription just in case."
Doesn't seem to be quite what an assistance would be writing down, one would hope.
Re: (Score:3)
I believe this is a speaker-independent test so you shouldn't expect results to be as good as a system that has learned your speech.
In the article they say that humans have about a 6% error rate on the same test.
Re: (Score:1)
Error rates for speak recognition varies greatly. 6.5% is very poor is it was trained explicitly on your voice, it is stellar performance if you are to interpret a random person with foreign accent.
While the article is sparse on details, the most common benchmark for speech recognition accuracy is the "Switchboard conversational speech recognition benchmark". I am assume they are referring to this test. The Switchboard benchmark test is made up of 40 phone conversations from native english speaking persons.
Re: (Score:1)
I know this is hard for you to understand, but some people like knowing that their actions and communications aren't being recorded or analyzed by anyone. The only way to guarantee this is by hosting your services on your own hardware.
Hello? This is a geek website. Well, it used to be.
Re: (Score:2)
99% of people already have this.
I am the 1%.
Re: (Score:2)
Sounds like your willy isn't that large...
Re: (Score:2)
Mozilla needs something else to do instead of working on Firefox.
At least they are no longer spending donor dollars on sponsoring surfing contests [mozilla.org].
Re:The ADD of Mozilla continues (Score:5, Insightful)
Actually Web browsers need to implement a standardized speech recognition API (WebSpeech --- https://developer.mozilla.org/... [mozilla.org]), so this work could and probably will become part of Firefox. We wouldn't want speech-dependent Web applications to suck in Firefox on Linux because Firefox doesn't have access to a quality recognizer on free operating systems, would we?
This sort of thing is why building and maintaining Firefox is tremendously expensive. http://robert.ocallahan.org/20... [ocallahan.org]
Re: (Score:2)
While I agree, the recognition should be weighted by context - so that keywords are recognized more readily. At least until natural language processing progresses by leaps and bounds from where we are now. And if there isn't a way for the server side to provide context hints, you'll want to process the voice server-side anyway.
Open Search (Score:1)
Re: (Score:2)
I'm sure it has been discussed, but it's a very difficult business to get into. Look at how Microsoft search quality has struggled for years with a much greater investment than Mozilla could ever afford.
Re: (Score:1)
OK Mozilla (Score:2)
Disconnect Alexa, SIRI and Google from the network, and shut them down.
I would like to buy a hamburger (Score:2)
They really need to train it on this...
https://www.youtube.com/watch?... [youtube.com]
Re:Technology does not include voice. (Score:4, Insightful)
> Why so many OK OK's to install an add-on?
Because i want to install add-ons and not let random sites, apps or other add-ons to be able to install add-on silently, just like the old activex in IE
> Why break old good ones?
Because old ones could touch and replace ANYTHING in the browser, so it was a huge security problem, performance problem and locked mozilla from making big changes, as it would break many extensions. They finally decided to break everything and define a proper add-on API, that can be stable, run in outside and locked processes and using multiple cpus. They didn't decide to break the add-on just to annoy you, they had very good reasons
> Why uncheck 5 boxes to get a blank new tab?
I do like the new start page... but if you do not, then the 5 boxes to disable all the start page features is not hard at all, you just need to do it once. Notice that all that info in local info, what you see It's flexible enough to please most people... and those that really want a empty page, it's there too. There is no default config that will make everyone happy
Re: (Score:2)
some users != all users
Again, it's not easy to make everyone happy