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

Introducing ChatGPT and Whisper APIs

openai.com

Post reply on HN
Print view View original

691–696 of 696 posts

Re: Introducing ChatGPT and Whisper APIs

#693

Post by LoganDark »

pksebben wrote: post #567
LoganDark wrote: post #491

Earlier quoted context omitted.

> porn is a major innovation driver because humans are thirsty creatures. Hehe, yeah. I'm personally waiting for a model that is good at nonhuman stuff. Not just furries... but the focus seems to be on human content for now.

train the porn model you want to see in the world

not enough funds or training data for that to be economical at the moment :(

Re: Introducing ChatGPT and Whisper APIs

#694

Post by freediver »

graderjs wrote: post #522

Wow not a single mention of Whisper this entire comment first page! I think Whisper is really cool: the large model can pull speech out of even heavily distorted (wind noise, clipping, etc) audio. I have a story to illustrate why running Whisper on your own locally is not so easy! Much easier to sign up to the OpenAI API. In my research I found that actually pre-processing the audio to reduce noise (using the IMO bes…

Thank you very much for this detailed walk through.

Re: Introducing ChatGPT and Whisper APIs

#695

Post by graderjs »

freediver wrote: post #694
graderjs wrote: post #522

Wow not a single mention of Whisper this entire comment first page! I think Whisper is really cool: the large model can pull speech out of even heavily distorted (wind noise, clipping, etc) audio. I have a story to illustrate why running Whisper on your own locally is not so easy! Much easier to sign up to the OpenAI API. In my research I found that actually pre-processing the audio to reduce noise (using the IMO bes…

Thank you very much for this detailed walk through.

You're welcome!

Re: Introducing ChatGPT and Whisper APIs

#696

Post by patricksamy »

banana_giraffe wrote: post #100
travisjungroth wrote: post #79

Earlier quoted context omitted.

You split up the audio and send it over in a loop. Pass in the transcript of the last call as the prompt for the next one. See item 2 here: https://platform.openai.com/docs/guides/speech-to-text/promp...

And: > we suggest that you avoid breaking the audio up mid-sentence as this may cause some context to be lost. That's really easy to put in a document, much harder to do in practice. Granted, it might not matter much in the real world, not sure yet. Still, this will require more hand holding than I'd like.

If that helps, just wrote a script to split the audio and use the prompt parameter to provide context with the n-1 segment transcription: https://gist.github.com/patrick-samy/cf8470272d1ff23dff4e2b5...
Post reply on HN