duerig
commented
1 year ago I did try this a number of years ago with some open source voice recognition at the time. One problem is that the vocabulary is very small and I understand that this creates a big problem with false positives. In my tests, for example, I found that it not only recognized my voice saying 'capture' as the capture command, it also recognized the sound of the camera shutters going off as the capture command. This created an eternal loop until I unplugged the microphone.
But it has been a long time since I tried it and there might be better accuracy now. Note that everything I did was doing local voice processing and not trying to upload anything to the 'cloud' because that would require a network and making sure the Pi is secure on that network.
On Sun, Sep 25, 2022, at 4:02 PM, Daniel Yacob wrote:
A wish list item is for voice command whereby you can speak a button label and pi-scan executes the action. This is most helpful for "Capture", but would be great for all buttons.
— Reply to this email directly, view it on GitHub https://github.com/Tenrec-Builders/pi-scan/issues/24, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAGWYTBUECWIUKEOKH3GCA3WADDXZANCNFSM6AAAAAAQVIN5V4. You are receiving this because you are subscribed to this thread.Message ID: @.***>
A wish list item is for voice command whereby you can speak a button label and pi-scan executes the action. This is most helpful for "Capture", but would be great for all buttons.