Live data from Hacker News

I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

news.ycombinator.com

11–20 of 129 posts

Re: I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

#14
I was surprised to learn that the

    M1 Max CPU is an ARM/SoC, comparable to an 11th gen Intel i9
Do I have it right? Would Windows ARM performance be similar for those cpu?

ref: https://www.cpubenchmark.net/compare/4585vs4245/Apple-M1-Max...

Re: I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

#16

Does it work for porn collections too?

Last time I tried whisper, it hallucinated an elaborate conversation from sounds of slapping and moaning and it took minutes to spit every single line of it.

Parakeet has been trained to detect non-voice sounds and exclude that from identification, so you might have better luck with that family.

Re: I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

#19

I was surprised to learn that the M1 Max CPU is an ARM/SoC, comparable to an 11th gen Intel i9 Do I have it right? Would Windows ARM performance be similar for those cpu? ref: https://www.cpubenchmark.net/compare/4585vs4245/Apple-M1-Max...

It's also a bit apples (heh) to oranges for a handful of reasons, but most impactful

- "unified" ram makes all the system ram available as VRAM - dedicated ai coaccelerator thingy

Both of these reasons allow the apple silicon chips to crush conventional cpus in these kind of AI model workload stuffs

No idea about what the windows arm stuff is capable of. I know they use Qualcomm snapdragon chips though.

Re: I indexed 669 GB of my GoPro videos using my M1 Max computer and local ML models

#20

Does it work for porn collections too?

You'll need a lora for this, porn content rejection is heavy. Or you'll need a abliterated model, not sure if vision also works. You might want to add something like yolo finetune to detect scenes + face recognition too.

Vision still works perfectly fine in abliterated models.
Post reply on HN