News for hackers. Stuff that matters.
Re:The era of open voice assistants has arrived by Jarwain on Thursday December 19, 2024 @11:20PM (#42468247)
I can't speak to home assistant specifically, but the last time I looked at voice models, supporting multiple languages and doing it Really Well just happens to require a model with a massive amount of RAM, especially to run at anything resembling real-time.

It's be awesome if they open sourced that model though, or published what models they're using. But I think it unlikely to happen because home assistant is a sorta funnel to nabu casa

That said, from what I can find, it sounds like Assist can be run without the hardware, either with or without the cloud upgrade. So you could definitely use your own hardware, headset, speakers, etc. to play with Assist

Re:The era of open voice assistants has arrived by frognumber on Friday December 20, 2024 @01:49PM (#42473697)
shrug whisper seems to do well on my GPU, and faster than realtime.
Re:The era of open voice assistants has arrived by Jarwain on Friday December 20, 2024 @02:24PM (#42474063)
Found what I was thinking of [1]

Part of my misremembering is I was thinking of smaller/iot usecase which, alongside the 10GB VRAM requirements for the large multilingual model, felt infeasible -shrug-

[1] https://git.acelerex.com/automation/opcua.ts/-/project_membe...

Re:The era of open voice assistants has arrived by paradox460 on Friday December 20, 2024 @06:22PM (#42476130)
I've been using it to generate subtitles for home movies, for an aging family member who is losing their hearing, and it's phenomenal