×

Please see all COVID-19 updates here as some shipments may be delayed due to CDC safety and staffing guidelines. If you have an order or shipping question please refer to our Customer Support page. For technical questions please check out our Forums. Thank you for your continued support.

MichaelCain

Member Since: January 20, 2010

Country: United States

  • I need voice recognition on a Pi-based system and have been fooling with the Vosk software. So far, I'm cheating: the Vosk server is running on my desktop Linux box and the Pi just pumps audio samples to it and parses the returned text strings. The small Vosk models (several languages available) are supposed to be capable of running on a Pi.

    In a controlled environment it's not too bad, but as I have it configured not really good enough to trust with wake words. It's a large vocabulary recognizer. One of the things on my to-do list is to look into giving it a much more limited dictionary. This is apparently straightforward -- not the same as simple -- and is supposed to improve accuracy.

  • The picture here shows what looks like spade connectors. The datasheet picture is screw connectors. Which is it?

  • Voltage levels. I kludged up the "normal" one-transistor level converter to take the PC's TX at RS232 levels to the backpack's RX at TTL levels out of parts I had at hand and it seems to work okay. Other than some of the complaints made above about slow response, etc.

  • For the moment, I'd like to send command strings to this from a PC. I've configured a serial port for 115,200 baud, 8N1. Something is clearly getting through, as the display adds a "character" for each keystroke. The character that gets displayed has no obvious correlation with the character I send, though. I can think of a number of things that could cause problems: voltage levels, slew rate (given test clip connectivity), subtle timing errors. Has anyone had any luck doing this?

No public wish lists :(