I've been using FFmpeg and Whisper to record and transcribe live police scanner audio for my city, and update it in real-time to a live website. It works great, with the expected transcription errors and hallucinations.

Is this website open? Would love to see your work :P

somerville.votolab.com

All the "Thanks for watching!" gave me a good chuckle.

Remind me of one of my own experiences with one of the Whisper model, where some random noise in the middle of the conversation was translated into "Don't forget to like and subscribe".

Really illustrate where the training data is coming from.

Looks like this is a nice case were the LLM thinks that silence is "thanks for watching" which was discussed on here a few days ago.

I wanted to do this for my local county council meetings. I think in this context speaker recognition would be important.

"I believe some folks in tech love to make simple things sound complex, maybe to seem more impressive."

Seems to apply here

I've been using excel1040.com for the last few years. It's an excel spreadsheet calculator, in the same format as all the tax forms.

You still have to know "how to do your taxes", but it takes away a lot of the busy work, and will flag certain things you may otherwise miss.

For at-will employment, employers can legally fire employees for unreasonable reasons, including unrealistic expectations of work performance.