DeepSpeech 60x Smaller, 9x faster, and 2x accuracy

https://github.com/Picovoice/leopard

by kenarsa • 4 years ago

75 26 4 years ago

github.com

themerone2• 4 years ago

Repo has Apache license, but is loaded with binary blobs and requires paid access keys.

spupe• 4 years ago

Title is very confusing. And there is no benchmark whatsoever to back up those claims.

moffkalast2• 4 years ago

Well there's this: https://raw.githubusercontent.com/Picovoice/speech-to-text-b...

So allegedly twice as accurate as Google Assistant, which sounds very impressive. No clue if it would run in real time on something like a Jetson Nano though.

kenarsa4• 4 years ago

Clarification. Google STT has to services. standard and enhanced. we are just better than enhanced and much better than standard. enhanced is much pricier than standard if you wonder what the diff is.

It runs real-time on NVIDIA Jetson Nano and RPI 3/4.

If you think we should consider other embedded platforms we love to hear what and why

colechristensen• 4 years ago

What are the state of the art open solutions to local voice recognition? Preferably with available models that a small org can also train themselves without millions in hardware.

albertzeyer• 4 years ago

Kaldi, K2, ESPNet.

misc1234• 4 years ago

Nemo

rileyphone2• 4 years ago

I will add https://github.com/coqui-ai/STT, which is a continuation of DeepSpeech. Also, I've been messing around with https://github.com/ideasman42/nerd-dictation, which works on a VOSK backend - accuracy is decent, especially with the bigger model.

trowngon• 4 years ago

Vosk https://github.com/alphacep/vosk-api

rhacker• 4 years ago

Title should be adjusted to:

Picovoice/leopard: On-device speech-to-text engine powered by deep learning

Since the claim is only in the HN title and not in the actually page that is linked.

froh• 4 years ago

Some benchmarks are here: https://github.com/Picovoice/speech-to-text-benchmark#result...

That is however not the linked page indeed.

kenarsa4• 4 years ago

Thank you for the clarification. `[1]` and `[2]` hyperlinks in the intro section point the benchmark

wantsanagent• 4 years ago

Is this OSS? It looks like it has licenses and account limits baked in. Or is the release under Apache a green light to strip all that out?

simcop2387• 4 years ago

Can't confirm but based on their site, I suspect that the code is OSS, but the model isn't. And that license to get the model from them is what you're getting. Not sure how they enforce or deal with the number of hours transcribed though because they say they don't collect data and the whole thing happens on device.

jka• 4 years ago

It would be great to have industry-recognized, concise terms for this kind of situation ("project is (FL)OSS, but contains proprietary machine learning").

For deployment of services we have "self-hosted", "cloud" and "on-prem", for example.

For ML-based projects could we have something like "teachable" (as in you can "raise" the model the way you would like to) vs "pre-directed"?

(it's been a long day; these probably aren't the neatest suggestions)

themerone2• 4 years ago

Definately not. The repo is full of precompiled dlls.

pumanoir• 4 years ago

Is there anything as accurate and as small but Open Source and no subscriptions? Or at least just a small tflite model with similar specs?

jijji• 4 years ago

it says its on device, but then mention its $899/month

gigel82• 4 years ago

You would need internet connectivity to validate your AccessKey with Picovoice license servers even though the voice recognition is running 100% offline.

Plus closed source binaries checked into GitHub which is always a red flag; you're basically using it for free distribution of your paid software.

kneel• 4 years ago

Paid software on github, this post is just an ad.

rileyphone2• 4 years ago

steps to try it out:

- sign up for an account to get an access key - install demos with `npm install -g @picovoice/leopard-node-demo` - run `leopard-mic-demo -a $ACCESS_KEY`

I'm pretty impressed with the accuracy, especially given it's all local and a 20MB model (though the total weight with node modules included comes out to 36MB). Obviously the licensing restrictions are a bummer, but 100 hours a month should be more than enough for my purposes - I like to compose thoughts with my voice sometimes and capture something as close to the stream of consciousness as possible. Really curious to see what gets built on this.

FloatArtifact• 4 years ago

Accuracy is important but latency plays an important role for viable speech recognition.

DeepSpeech 60x Smaller, 9x faster, and 2x accuracy

Related Stories