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

Re:DeepSpeech 60x Smaller, 9x faster, and 2x accuracy by spupe on Wednesday March 09, 2022 @12:05PM (#30616961)

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

[ Parent | on HN ]

Re:DeepSpeech 60x Smaller, 9x faster, and 2x accuracy by moffkalast on Wednesday March 09, 2022 @12:23PM (#30617274)

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.

[ Parent | on HN ]

Re:DeepSpeech 60x Smaller, 9x faster, and 2x accuracy by kenarsa on Wednesday March 09, 2022 @01:32PM (#30618249)

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

[ Parent | on HN ]

Re:DeepSpeech 60x Smaller, 9x faster, and 2x accuracy by moffkalast on Wednesday March 09, 2022 @06:16PM (#30621262)

> and RPI 3/4

Woah, now that is cool. Are you guys considering a Mycroft integration at some point?

[ Parent | on HN ]

Re:DeepSpeech 60x Smaller, 9x faster, and 2x accuracy by kenarsa on Wednesday March 09, 2022 @08:07PM (#30622061)

mycroft already integrated our wake word (porcupine). we remain neutral and anyone can use our tech :)

[ Parent | on HN ]