Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI charges by the minute, so speed up your audio

george.mand.is

Post reply on HN
Print view View original

211–220 of 234 posts

Re: OpenAI charges by the minute, so speed up your audio

#211

Post by Philip-J-Fry »

dogprez wrote: post #196
jwrallie wrote: post #159

Earlier quoted context omitted.

From my own experience with whisper.cpp, normalizing the audio and removing silence not only shortens the process time significantly, but also increases a lot the quality of the transcription, as silence can mean hallucinations. You can do that graphically with Audacity too, if you do not want to deal with the command line. You also do not need any special hardware to run whisper.cpp, with the small model literally a…

Others pointed out the value of silence, but I just wanted to say it saddens me when humanity is misclassified as inefficiency. The other day Sam Altman made a jest about how much energy is wasted by people saying "thanks" to chatgpt. The corollary is how much human energy is wasted on humans saying thanks to each other. When making a judgement about inefficiency one is making a judgement on what is valuable, a very…

Well, humans saying thanks to eachother isn't wasted energy. It has a real affect on our relationships.

People say thank you to AI because they are portrayed as human-like chat bots, but in reality it has almost no effect on their effectiveness to respond to our queries.

Saying thank you to ChatGPT is no less wasteful than saying thank you to Windows for opening the calculator.

I don't think anyone is trying to draw any parallels between that inefficiency and real humans saying thank you?

Re: OpenAI charges by the minute, so speed up your audio

#212

Post by rz2k »

kristianbrigman wrote: post #208
dogprez wrote: post #196

Earlier quoted context omitted.

Others pointed out the value of silence, but I just wanted to say it saddens me when humanity is misclassified as inefficiency. The other day Sam Altman made a jest about how much energy is wasted by people saying "thanks" to chatgpt. The corollary is how much human energy is wasted on humans saying thanks to each other. When making a judgement about inefficiency one is making a judgement on what is valuable, a very…

I’ll remember that you told me thanks. Will chatgpt? (Honestly curious… it’s possible)

I get the impression that it sets a tone that encourages creative, more open ended responses.

I think this is the reverse of confrontation with the LLM. Typically if you get a really dumb response, it is better to hang up the conversation and completely start over than it is to tell the LLM why it is wrong. Once you start arguing, they start getting stupider and respond with even faultier logic as they try to appease you.

I suppose it makes sense if the training involves alternate models of discourse resembling two educated people in a forum with shared intellectual curiosity and a common goal, or two people having a ridiculous internet argument.

Re: OpenAI charges by the minute, so speed up your audio

#213

Post by hooverd »

Der_Einzige wrote: post #192
nickjj wrote: post #119

Earlier quoted context omitted.

Andrej's talk seemed normal to listen at 2x but I've also listened to everything at 2x for a long time. Unfortunately a byproduct of listening to everything at 2x is I've had a number of folks say they have to watch my videos at 0.75x but even when I play back my own videos it feels painfully slow unless it's 2x. For reference I've always found John Carmack's pacing perfect / natural and watchable at 2x too. A recent…

This btw is also why spreading (speed reading) happens in American competitive debate. This gets ridiculed online but it's exactly why it happens. https://en.wikipedia.org/wiki/Spreading_(debate)

They should put an upper WPM on competitive debate, like F1 does with certain car parts.

Re: OpenAI charges by the minute, so speed up your audio

#214

Post by mulmen »

dogprez wrote: post #196
jwrallie wrote: post #159

Earlier quoted context omitted.

From my own experience with whisper.cpp, normalizing the audio and removing silence not only shortens the process time significantly, but also increases a lot the quality of the transcription, as silence can mean hallucinations. You can do that graphically with Audacity too, if you do not want to deal with the command line. You also do not need any special hardware to run whisper.cpp, with the small model literally a…

Others pointed out the value of silence, but I just wanted to say it saddens me when humanity is misclassified as inefficiency. The other day Sam Altman made a jest about how much energy is wasted by people saying "thanks" to chatgpt. The corollary is how much human energy is wasted on humans saying thanks to each other. When making a judgement about inefficiency one is making a judgement on what is valuable, a very…

Humans are inefficient. The mistake is making a moral judgement about that.

Re: OpenAI charges by the minute, so speed up your audio

#215

Post by 7speter »

So wait… is whisper transcription really all that slow locally on a M3 Macbook? It’s been a while since I used whispercpp, but I seem to remember it taking maybe 20 minutes on a comparatively slowpoke (and powerhungry) i5 12600k for maybe 40 minutes of audio; it might take less time on a faster m chip (maybe I’m imagining mobile apple silicon to be more performant than even desktop intel cpus), even less if there support built in for the built in gpu cores and other ai optimized silicon?

Did I miss that the task was time sensitive?

Re: OpenAI charges by the minute, so speed up your audio

#216

Post by janalsncm »

tucnak wrote: post #175
maxall4 wrote: post #98

Earlier quoted context omitted.

Just count syllables per second by doing an FFT plus some basic analysis.

> FFT plus some basic analysis Yeah, totally easier than `len(transcribe(a))/len(a)`

Maybe not as quick to code up but way faster to calculate.

The tokens/second can be used as ground truth labels for a fft->small neural net model.

Re: OpenAI charges by the minute, so speed up your audio

#217

Post by zamadatix »

K2L8M11N2 wrote: post #144
zamadatix wrote: post #132

Earlier quoted context omitted.

YouTube ran an experiment with up to 4x playback on mobile (???) but it went away in February. I get a lot of the experiments they do being experiments but why just allowing the slider to go farther is such a back and forth hoopla is beyond me. It's one of the oft touted features of 3rd party apps and extensions with nearly 0 UI impact to those who don't want to use it (just don't slide the slider past 2x if you don'…

As a premium subscriber I currently have 4x available on Android and they recently (in the last month) added it to web too

As a premium subscriber I no longer have 4x available on iOS and I never had it on web. I also no longer see it as an experiment on https://www.youtube.com/new

I hope they make up their mind on it soon instead of this endless A/B testing.

Re: OpenAI charges by the minute, so speed up your audio

#218

Post by satvikpendem »

ilyakaminsky wrote: post #87
bravesoul2 wrote: post #7

Earlier quoted context omitted.

You could have kept quiet and started a cheaper than openai transcription business :)

I've already done that [1]. A fraction of the price, 24-hour limit per file, and speedup tricks like the OP's are welcome. :) [1] https://speechischeap.com

Can it do real-time transcription with diarization? I'm looking for that for a product feature I'm working on. Currently I've seen Speechmatics do this well, haven't heard of others.

Re: OpenAI charges by the minute, so speed up your audio

#219

Post by satvikpendem »

BrunoJo wrote: post #154
rob wrote: post #33

For anybody trying to do this in bulk, instead of using OpenAI's whisper via their API, you can also use Groq [0] which is much cheaper: [0] https://groq.com/pricing/ Groq is ~$0.02/hr with distil-large-v3, or ~$0.04/hr with whisper-large-v3-turbo. I believe OpenAI comes out to like ~$0.36/hr. We do this internally with our tool that automatically transcribes local government council meetings right when they get uplo…

Let me know if you are interested in a more reliable transcription API. I'm building Lemonfox.ai and we've optimized our transcription API to be highly available and very fast for large files. Happy to give you a discount (email: bruno at lemonfox.ai)

Can it do real-time transcription with diarization?

Re: OpenAI charges by the minute, so speed up your audio

#220

Post by weq »

bisby wrote: post #80
pluc wrote: post #15

Earlier quoted context omitted.

Seriously this is bonkers to me. I, like many hackers, hated school because they just threw one-size-fits-all knowledge at you and here we are, paying for the privilege to have that in every facet of our lives. Reading is a pleasure. Watching a lecture or a talk and feeling the pieces fall into place is great. Having your brain work out the meaning of things is surely something that defines us as a species. We're wil…

> I, like many hackers, hated school because they just threw one-size-fits-all knowledge at you "This specific knowledge format doesnt work for me, so I'm asking OpenAI to convert this knowledge into a format that is easier for me to digest" is exactly what this is about. I'm not quite sure what you're upset about? Unless you're referring to "one size fits all knowledge" as simplified topics, so you can tackle things…

In the coming years, you will be paying AI companies a cut of your salary. It will be the cost of doing buisness. People will be so dumb they wont be able to tell whats an AI halluciation or not. We will continue to enter our every thought into the AI until it can replace us at that task. Your job will become AI slop input -> AI slop output. Everyone will conform on a natural optimisation point.

This all discounts how human variation and thinking is critical to the advancement and survival of the species being adaptable as possible to the climate and conditions of the given day. We didnt get to moon on the back of one person or race. The AI can only emulate what it sees, it cant have ideas of its own. The dawn of AI will never be seen again, all AI will suffer from the collective delusion to the point your freedom will be defined by not truth.

https://tech.co/news/another-study-ai-making-us-dumb

Post reply on HN