Hacker News new | past | comments | ask | show | jobs | submit | more ax8080's comments login

Thank you! Yes, I'll definitely do that. That's on the list!


Yes, it's still far from perfect, sorry about that. And it's not about the GPT. I'm sure I can greatly increase the quality on my side.


If you have access to chapter markers, that might be a solid way to segment


Your app is slick and works great. How can you increase the quality? I thought you just pass the subtitles to chatgpt and return the results?


It's not that straightforward. I would say that the most important part of pre-processing is how to break the transcript into parts.

But there are many more things to improve. It's a pipeline: you can add more models, you can train them, you can change prompts, you can post-process the results. But it takes time. More time each step.


Ah ok then maybe I was too harsh. Your app is pretty cool. Great job!


Oh, it's okay! In the end, what matters is how much value it gives the user, not how complicated it is inside! thank you!


I have tried many (all the popular) huggingface summarization models, they don't compare to GPT. Basically, they highlight the parts they think are important. But they can't "understand" and generalize.

Frankly, I haven't read the papers about summarization. But I will have to when I'll work on reducing costs.


I see, thank you for the insight. The OpenAI paper about summarization is an easy read and very similar to your approach, if you are looking for somewhere to start: https://openai.com/blog/summarizing-books/.


That’s commonly referred to as abstractive vs extractive summarisation


You can buy the "package" for now :) Subscriptions will be ready by Monday or Tuesday!


I will definitely do that!


WOW! What do you use to generate voice? It's SO scary similar to real podcasts. I couldn't find it in a minute in the sources.


and it's funny how sometimes it makes ahhrhrhrhrhhhhh sounds what is the reason behind that?


It happens quite often with TorToiSe that it collapses in this way. Especially for unseen tokens that wouldn't have appeared in the training data, which likely consisted of a lot of transcribed stuff and read text like audio books. Trying to make it laugh by prompting it with "hahaha" (which you won't really see in mentioned data) often gets you demon and zombie noises.



I wonder why the title says that it uses Tortoise TTS?

Also interesting that play.ht allows you to clone others' voices.


How did they get to use the joe rogan voice though? It seems that one isn’t public?


It uses the TorToiSe TTS model for generation. It's simple to generate conditioning voice latents using short audio samples. Likely transcribed JRE episodes were part of the TorToiSe training data, explaining how it's so good at recreating his voice characteristics in particular.


That generation uses tortoise-tts. Play.ht has a model called peregrine, I've taken to using a script to call them out. Super cool company & API. I just haven't had time to get my next gen version out.


Play.ht


Interesting application! It hadn't occurred to me. To my shame, the best I've come up with is to cut ads from influencers videos (make a rewind button).


I'll chime in with hearty agreement. Being able to let my son watch what he finds without my having to watch it all first (as I do now)? I hope this product/service is available in about 4-5 years, when he's at an age where his interests will hopefully start diverging from ours.

There are probably loads of other parents who would love this.


After installing the extension, go to youtube. There is a "Sign in with Google" button where "related videos" are usually located. If something went wrong, please send a screenshot to me at support@eightify.app


I see it now, had to turn off adblock


When I first got to know it, there wasn't much good resources. And now there are 100 times more articles, but I haven't watched them. So I can't recommend anything yet.

Oh yes, I remembered that I saw this - it's good advice: https://help.openai.com/en/articles/6654000-best-practices-f...


I launched it on Product Hunt last week. I've been tweaking and fixing bugs since then and have now published it here.

Thank you!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: