i'm amazed at the transcription quality here. i spent a couple minutes listening, just in awe at the often nearly unintelligble crackling over the speakers, and then a half second later it prints a transcription that seems totally plausible to what i just heard, but without the transcription i don't think i would have been able to understand it.

▲

russellbeattie 3 hours ago | parent [-]

I've honestly never understood how pilots or the tower are able to understand anything that's happening over the radio. Not only is there always constant static and interference, but they all speak in short rapid fire bursts that even beyond the lingo and shorthand is hard to process. I'd never be able to get a pilot's license.

"Delta blarg-mumble-twenty-blurgle-fargle-*screeeeeeeech*eading-foxtrot-squidgle-skee thanks."

It's absolutely amazing that the AI model is able to transcribe all that noise.

▲

dghlsakjg 2 hours ago | parent | next [-]

90% of radio communications is standard and expected.

If I get the call sign and a few key words, I can normally figure it out. For the most part you kinda know what people are gonna say before they say it, or at least have it narrowed down to just a few possibilities. You also just get an ear for the narrowband AM sound after a few hours.

“(Garbled) n123a (garbled) joining (garbled) one three” heard at an untowered field is going to be “local traffic, Cessna N123a is joining the downwind leg for runway 13.”

Or if you’re on final approach and the tower calls you up, there are really only a few things they are going to tell you, most likely is “Cessna 123a cleared to land”.

Plus, I’m guessing you have o my listened to very busy feeds at commercial airports. Students at smaller airports will often announce that they are a student, and controllers and other pilots will try to slow it down and give them a little extra room and time.

No idea how AI does it, but I assume it’s not too hard since there are essentially unlimited hours of recording to train on.

	▲	notatoad an hour ago \| parent [-]
		i'm guessing the model is doing something similar, and has a fairly confident set of the possible phrases to map sounds to.

▲

cullenking 41 minutes ago | parent | prev [-]

In the air it’s usually way more clear than the stuff you hear on liveatc etc. if I’m 5k above terrain, have a nice radio and antenna, I have a solid 50+ mile range with anything local being quite clear. Ground recorders have way worse reception unless someone rented space on a tower.