minus-squareNorah - She/TheylinkfedilinkEnglisharrow-up2·1 year agoHope you like 40 second response times unless you use a GPU model.
minus-squareJDubbleu@programming.devlinkfedilinkarrow-up10·1 year agoI’ve hosted one on a raspberry pi and it took at most a second to process and act on commands. Basic speech to text doesn’t require massive models and has become much less compute intensive in the past decade.
minus-squareNorah - She/TheylinkfedilinkEnglisharrow-up2·1 year agoOkay well I was running faster-whisper through Home Assistant.
Hope you like 40 second response times unless you use a GPU model.
I’ve hosted one on a raspberry pi and it took at most a second to process and act on commands. Basic speech to text doesn’t require massive models and has become much less compute intensive in the past decade.
Okay well I was running faster-whisper through Home Assistant.