this post was submitted on 22 Nov 2023
176 points (100.0% liked)

196

16442 readers
2620 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS
moss@lemmy.blahaj.zone
greembow@lemmy.blahaj.zone
moss@lemmy.world
queue@beehaw.org
funky_rodent@lemmy.blahaj.zone
PeachyMcPeachface@lemmy.blahaj.zone
threegnomes@lemmy.blahaj.zone
greembow@lemmy.world
remotelove@lemmy.ca
Roflmasterbigpimp@feddit.de
qaz@lemmy.world
A_Very_Big_Fan@lemm.ee
qaz@lemmy.blahaj.zone
qaz@lemmy.ca
A_Very_Big_Fan@lemmy.world
qaz@lemmy.dbzer0.com
Qaz@lemmy.ml
qaz@sh.itjust.works
qaz@lemmy.sdf.org
176
Ruletanic (lemmy.blahaj.zone)
submitted 11 months ago by outer_spec@lemmy.blahaj.zone to c/196@lemmy.blahaj.zone
7 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] sharkfucker420@lemmy.ml 16 points 11 months ago (1 children)

There are locally hosted (not connected to internet) home assistants. They take more setup but are a lot more customizable, especially the open source ones.

[–] princessnorah@lemmy.blahaj.zone 2 points 11 months ago (1 children)

Hope you like 40 second response times unless you use a GPU model.

[–] JDubbleu@programming.dev 10 points 11 months ago (1 children)

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.

[–] princessnorah@lemmy.blahaj.zone 2 points 11 months ago

Okay well I was running faster-whisper through Home Assistant.