Live data from Hacker News

Serverless Video Transcription inspired by Cyberpunk 2077

github.com

51–60 of 84 posts

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#51

I developed an online course on serverless machine learning, where you can learn some of the principles of refactoring ML systems into separate feature/training/inference pipelines: https://github.com/featurestoreorg/serverless-ml-course Some of the students have built similar systems, for example chaining Whisper and ChatGPT or translation or sentiment analysis of transcribed text, such as here (transcribe Swedish a…

Why is this type of cloud based computing called serverless?

To me "putting all the work on remote machines you don't manage" seems pretty cloudy, and I naively expected "serverless" to mean something like runs locally, not "uses a shit town of someone else's servers".

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#52

I developed an online course on serverless machine learning, where you can learn some of the principles of refactoring ML systems into separate feature/training/inference pipelines: https://github.com/featurestoreorg/serverless-ml-course Some of the students have built similar systems, for example chaining Whisper and ChatGPT or translation or sentiment analysis of transcribed text, such as here (transcribe Swedish a…

Why is this type of cloud based computing called serverless? To me "putting all the work on remote machines you don't manage" seems pretty cloudy, and I naively expected "serverless" to mean something like runs locally, not "uses a shit town of someone else's servers".

Great question. I think of it as follows - if I can just write some operational Python code and "deploy" it, without needing to install/upgrade/maintain systems software (k8s/DB/feature-store/etc), then I have built a serverless system. What's cool now is lots of these services have great free tier and you can run serverless ML systems without paying anything.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#54
post #16

I'm really hoping somebody comes along and puts this in a format that I can attach to my head inconspicuously.

Google Glass has already been rejected by the public; I imagine anything more inconspicuous would arouse even deeper suspicion.

It was rejected because it didn't do anything useful. Certainly there are many really useful things we could do now that were not possible when it was first released, no?

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#55
post #19

People complain that the magic of programming has been lost because all we do is stitch together APIs. They're oversimplying the work done, those people are cynical, this is amazing.

Compare it to cars. New cars are more complex but collectors pay the most for the old, simple cars with a bonus for beauty and speed.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#56

I developed an online course on serverless machine learning, where you can learn some of the principles of refactoring ML systems into separate feature/training/inference pipelines: https://github.com/featurestoreorg/serverless-ml-course Some of the students have built similar systems, for example chaining Whisper and ChatGPT or translation or sentiment analysis of transcribed text, such as here (transcribe Swedish a…

Why is this type of cloud based computing called serverless? To me "putting all the work on remote machines you don't manage" seems pretty cloudy, and I naively expected "serverless" to mean something like runs locally, not "uses a shit town of someone else's servers".

Good question. For me it's in the same category as "hoverboards" that don't actually hover.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#57
post #55
post #19

People complain that the magic of programming has been lost because all we do is stitch together APIs. They're oversimplying the work done, those people are cynical, this is amazing.

Compare it to cars. New cars are more complex but collectors pay the most for the old, simple cars with a bonus for beauty and speed.

On your old car, you can just take it apart and see how it works. Don’t have the part? Improvise. It’s heavily skill-based, and a little knowledge will take you a long way. As long as you know your fundamental toolchains, you can make any part, do any job.

On your new car, it’s a series of black boxes, cables, and tubes - you don’t know and don’t care what happens inside the boxes, just what goes in, and what comes out. It’s heavily knowledge based - you need to know an awful lot about the boxes and how to work with them - but nobody expects you to machine your own parts. If one isn’t made that suits your purposes, you have to go to an old car guy.

The skillsets are similar but different. To be clear, I really am talking about cars and mechanics here - you won’t find many who can fix up both a 1960 and a 2021 motor. You’ll find plenty who can do one or the other, however.

And yeah - the same applies to developers.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#58
post #18
post #14

Earlier quoted context omitted.

I think you are referring to GE2E [1], which is the speaker identification model used in that project. [1] https://arxiv.org/abs/1710.10467

That's from an eternity ago. Speaker diarization has come a long way.

What's the best pretrained model available? The best I've tried is pyannote.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#59
post #53

Does anyone have a link to something similar for real-time captions (audio only - (.g. Google Meet, Twitter Spaces)? Or is that typically done on the device itself

If I understood you correctly, there's a Chrome accessibility feature that you should check out: https://support.google.com/chrome/answer/10538231

Think of it as YouTube's auto-generated captions, but on a browser level.

Re: Serverless Video Transcription inspired by Cyberpunk 2077

#60

I developed an online course on serverless machine learning, where you can learn some of the principles of refactoring ML systems into separate feature/training/inference pipelines: https://github.com/featurestoreorg/serverless-ml-course Some of the students have built similar systems, for example chaining Whisper and ChatGPT or translation or sentiment analysis of transcribed text, such as here (transcribe Swedish a…

Why is this type of cloud based computing called serverless? To me "putting all the work on remote machines you don't manage" seems pretty cloudy, and I naively expected "serverless" to mean something like runs locally, not "uses a shit town of someone else's servers".

A good analogy I heard is that serverless uses servers as much as wireless uses wires. It does, but it's not part of your responsibility.
Post reply on HN