Picovoice – Embed private voice AI into any product instantly

Re:Picovoice – Embed private voice AI into any product insta... by syntaxing on Friday October 12, 2018 @11:38AM (#18202158)

I would love to see some benchmark numbers on Picovoice. The small size and low CPU is definitely interesting but I'm worried that performance is hindered because of this. Also, is 8% peak usage? Having this loaded on some small IoT chip will be awesome to see.

[ Parent | on HN ]

Re:Picovoice – Embed private voice AI into any product insta... by kenarsa on Friday October 12, 2018 @11:44AM (#18202206)

You should check this out: https://github.com/Picovoice/wakeword-benchmark

We do work with a couple of SoC manufacturers and will disclose some of the results when our partners are ready. In general, we can run on any MCU with a C compiler and 200KB of RAM (maybe less if there is fast FLASH available). We already of models working on ARM Cortex-M and Cadence's HiFi4.

[ Parent | on HN ]