Whisper really is a lot better when it works, and it’s free. The problem is that it refuses to produce gibberish or give up when it doesn’t work. You’ll always need an editor.
Comment on Researchers say an AI-powered transcription tool used in hospitals invents things no one ever said
ShittyBeatlesFCPres@lemmy.world 3 weeks ago
Why is generative AI even needed for audio transcription? We’ve had decent voice recognition tools for years even on cheap consumer grade stuff.
TheBlackLounge@lemm.ee 3 weeks ago
Assman@sh.itjust.works 3 weeks ago
The toaster oven I just invented works much better than a traditional one. It reheats French fries perfectly, you can dehydrate in it, makes succulent roasted chicken, and about 2.5% of the time it burns down your house. You’ll always need to keep an eye on it to make sure that doesn’t happen. Remember though, much better than a traditional one.
superkret@feddit.org 3 weeks ago
Can I try the chicken before I make a decision?
TheBlackLounge@lemm.ee 2 weeks ago
You need an editor for traditional transcription tools too :) and it’s A LOT more work. They don’t even do punctuation or names.
wdx@feddit.org 3 weeks ago
This definition of “better” feels like claiming that a Beeper that’s constantly hooked to power is the perfect alarm because it warns you every time someone is trying to break in - while entirely ignoring that it is just constantly blaring.
TheBlackLounge@lemm.ee 2 weeks ago
I use it for generating subtitles. It figures out context, it ignores stuttering, it does punctuation etc. It’s really is just better. With clean audio it transcribes like a human does.
It does better than other techniques with dirty audio, but when it fails it fails weird, which is the big issue here.
ayyy@sh.itjust.works 3 weeks ago
No, we really haven’t had on-device voice recognition that meets any definition of “decent”. Anything reasonable phones out to “the cloud” for decent voice recognition.
LavenderDay3544@lemmy.world 2 weeks ago
So? I’d rather have my software talk to a server than be downright wrong just so another business can climb onto the AI bandwagon.
Szyler@lemmy.world 2 weeks ago
You can’t do that with personal information like the ones doctors needs transcribed. It has to be local.
ayyy@sh.itjust.works 2 weeks ago
Reality is more nuanced than this. You can absolutely be HIPAA compliant while using “cloud” servers as long as they are sufficiently isolated and secured. The requirements are definitely insufficient to protect your data from a Motivated State Actor™ but they are good enough to keep your data away from an abusive family member or crazy ex. I have worked on systems that handle patient data as well as other systems with restrictions I can’t discuss and I can assure you patient data is much easier to move around and handle compared to state secrets.
JeeBaiChow@lemmy.world 3 weeks ago
Because AI!
spankmonkey@lemmy.world 3 weeks ago
We also used to have decent web searches!
InverseParallax@lemmy.world 3 weeks ago
Because with normal algorithms you have someone to blame.
AI is a trick to hide when you steer the results the way you want.