Got a local running AI on Sunday that will be able to transcribe literally my entire podcast and I can fully automate the process with some basic shell scripting… and then in under 2 days I may have found another AI that will do it with half the error rate, can add translation to 102 languages, and can do it even faster…
If you want unlimited free transcription and translation, I’ll have a video on it soon #AI_Unchained
#grownostr
BITCOIN AUDIBLE FOR THE WORLD!
That would be awesome 👏
Are these things that need a high end rig to run or could they run on your average consumer desktop?
Would be good to have some serious compute, but it can be run on a typical “nice” consumer machine without being too much of a hog. Though you’ll want a C++ port of whatever is being run because python is just a monster of computational inefficiency.
With that said, I’m hoping to see a working release of Mojo (a new programming language that bridges between python and base hardware) that at a short glance looks like it will utterly change the game in this regard. Preliminary is looking to be in the 100x range performance improvement without having to change the program/model at all.
So, in a nutshell:
• Right now, yes-ish. If you know what you are looking for and are ok with some minor trade offs.
• In the near future, more yes. I expect more people porting the open source tools to more base languages like C++ and the like.
• In 2 years, absolutely, without question, 100%. We will be able to run multiple of these tools in real time on a huge variety of hardware. While the models will get both better and smaller at the same time. Both the use of current hardware will be vastly more efficient, AND all new processors will be optimized for AI. (literally every chip manufacturer right now is optimizing their next generation for AI, literally ALL of them)
I think there will be a Moore’s Law on top of Moore’s Law when it comes to these AI tools and their growing capacity, their improving accuracy, and the lowering of costs needed to run them.
Are you using Whisper? I found that it worked really well to caption a ton of YouTube videos.
Whisper is what I started with. The python version is slow as ass. But I found a C++ version that runs really smooth.
Now I’m exploring another one that I’m a little confused on how to get running, but when I figure it out and prove whether it’s actually better and can do the things it claims, I’ll update.
Please do! Would be glad to hear what you find. By the way, I’m excited to hear you explore AI more in your new podcast.
Can I take your transcripts and run AI to create the Bitcoin Audible, Audible podcast with a Irish girl voice?
Irish Girl Bitcoin Audible is everything I need in this world.
There is a podcast with hundreds of hours of audio that I’d love to have transcripts of because I would like to feed those transcripts into gpt4all so I can ask it questions about them.
Trust me, there are things happening that will make this a reality faster than you may be aware 😘
So you'll read an article out loud, put in on a podcast, and then ask AI to give you back the article? The software for this should be named dickbutt. 🤣
But seriously, I'm excited about the ability to have my own 1-1 Q&A with smart AI who listened to more bitcoin podcasts than anyone else.
- what a way to accelerate learning
Haha, nah the transcriptions are for the Guy’s take afterwards 😂
However, one cool thing that I might want to work out, is actually having it transcribe and compare to the article in order to teach it words and emphasis based on my reading. Having the text and then my reading of it could potentially make my building a custom “Guy Swann AI” a really interesting and possibly valuable endeavor.
I'm waiting for you to train your ai to do the readings for you in your voice. Then you can simply listen to yourself read the article & go straight into Guy's take.
😂
Yes. 👍👍👍
