Our team is working with soniox.com They are the most acurate model that works real time.
OpenAI charges by the minute, so speed up your audio
221–230 of 234 posts
Re: OpenAI charges by the minute, so speed up your audio
#222Earlier 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…
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…
Saying thank you might still make sense in theory with AI, if AI used this as a clue to learn how useful the response was. Currently there is thumbs up and down, but it is very possible that there are mid conversation effects of it in the same context.
Re: OpenAI charges by the minute, so speed up your audio
#223It's also rude to talk slow to them. Unless its Siri.
Re: OpenAI charges by the minute, so speed up your audio
#224Earlier 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 and here we are, paying for the privilege to have that in every facet of our lives. But now we get to browse the knowledge rather than having it thrown at us. That's more important than the quality or formatting of the content.
We were already able to browse the knowledge. AI is throwing it's conclusions at us without having us go through the understanding process.
Re: OpenAI charges by the minute, so speed up your audio
#225You'd need a WER comparison to check if it really is no drop in quality. With this trick, there might be trouble if the audio is noisy, and it may. ot always be obvious whether or not to speed up.
Re: OpenAI charges by the minute, so speed up your audio
#226If you are hosting whisper yourself, you can do something slightly more elegant, but with the same effect. You can downsample/pool the context 2:1 (or potentially more) a few layers into the encoder. That allows you to do the equivalent of speeding up audio without worry about potential spectral losses. For whisper large v3, that gets you nearly double throughput in exchange for a relative ~4% WER increase.
Do you have more details or examples on how to downsample the context in the encoder? I treat the encoder as an opaque block, so I have no idea where to start.
It's a very simple change in a vanilla python implementation. The encoder is a set of attention blocks, and the length of the attention can be changed without changing the calculation at all.
Here(https://github.com/openai/whisper/blob/main/whisper/model.py...) is the relevant code in the whisper repo. You'd just need to change the for loop to an enumerate and subsample the context along its length at the point you want. I believe it would be:
for i, block in enumerate(self.blocks): x = block(x) if i==4: x = x[,,::2]
Re: OpenAI charges by the minute, so speed up your audio
#227Earlier quoted context omitted.
I came here to ask the same question. This is a well-solved problem, red queen racing it seems utterly pointless, a symptom of reflexive adversarialism.
> symptom of reflexive adversarialism Is there a definition for this expression? I don't catch you. > ... using corporate technology for the solved problem is a symptom of self-directed skepticism by the user against the corporate institutions ... Eh?
Reflexively adopting an adversarial approach (trying to outwit Open AI by using sped-up audio) instead of being content with the perfectly reliable, free, and quite efficient solution that already exists.
>> ... using corporate technology for the solved problem is a symptom of self-directed skepticism by the user against the corporate institutions ...
> Eh?
I don't know who wrote that or why you pasted in response to me.
Re: OpenAI charges by the minute, so speed up your audio
#228If you're already doing local ffmpeg stuff (i.e. pretty involved with code and scripting already) you're only a couple of steps more away from just downloading the openai-whisper models (or even the faster-whisper models which runs about two times faster). Since this looks like personal usage and not building production quality code, you can use AI (e.g. Cursor) to write a script to run the whisper model inference in…
Have you tried faster-whisper and whisper.cpp?
Re: OpenAI charges by the minute, so speed up your audio
#229That's a clever idea. Their are alternatives to OpenAI for audio transcription. Check them out https://www.addaidirectory.com/categories/audio or scroll the home page https://www.addaidirectory.com for updates
Re: OpenAI charges by the minute, so speed up your audio
#230If you're already doing local ffmpeg stuff (i.e. pretty involved with code and scripting already) you're only a couple of steps more away from just downloading the openai-whisper models (or even the faster-whisper models which runs about two times faster). Since this looks like personal usage and not building production quality code, you can use AI (e.g. Cursor) to write a script to run the whisper model inference in…
Have you tried faster-whisper and whisper.cpp?
Yeah, my mentioned times are with faster-whisper, but I have not tried whisper.cpp. I just use a python script to run the model.