Nice tutorial Jeremy. Is it possible to make an interface where my live recording through gets into text realtime? Btw time is a concern. Even if it takes few mins thats fine. Bt from mic to transcription would be cool and has lots of scope and use cases
ya know, somewhere in your description you should mention that your tutorial is for a Linux environment because , you know, most people that click on the link will be using Windows.. Just a though... huh!
@@otox7786 I should have mentioned this in the original post but notwithstanding that I am using Windows.... I know, I tried Ubuntu but just couldn't quite make the jump, in any case my point is that althouth your video is not going to help me I still appreciate that you took the time to try to help, CHeers.
@@Rabid-Pinocchio yeah same i appreciate his work, but i don't get why people don't create some like local gui for this, i found nothing like that, do you know something similar?
@@otox7786 Yes, as a matter of fact I do. I keep having an issue but I think it's because I installed the wrong version of Python or mixed up what version of Pytorch or something but now I keep having problems, that said I ran the script that is detailed in the following video, it is just one single copy/paste of the script into powershell, I ran it, it worked great but something at my end is screwing up, anyway check out this video search for, One-Click Whisper Install - Windows Install Script It's a One stop shop for whisper install
Yes, I should have mentioned that the process is the same in Windows if you have Python set up. You can also use WSL. However you have to deal with Windows. I've never had a good experience with Windows and Python, especially when working with AI/ML stuff.
Thank you for this ! Works well
Nice tutorial Jeremy. Is it possible to make an interface where my live recording through gets into text realtime? Btw time is a concern. Even if it takes few mins thats fine. Bt from mic to transcription would be cool and has lots of scope and use cases
It's definitely possible, though I've never done it before. That might be something I can try soon.
You can already do that using google docs. Google "type and edit with voice in google docs"
ya know, somewhere in your description you should mention that your tutorial is for a Linux environment because , you know, most people that click on the link will be using Windows.. Just a though... huh!
so right
@@otox7786 I should have mentioned this in the original post but notwithstanding that I am using Windows.... I know, I tried Ubuntu but just couldn't quite make the jump, in any case my point is that althouth your video is not going to help me I still appreciate that you took the time to try to help, CHeers.
@@Rabid-Pinocchio yeah same i appreciate his work, but i don't get why people don't create some like local gui for this, i found nothing like that, do you know something similar?
@@otox7786 Yes, as a matter of fact I do. I keep having an issue but I think it's because I installed the wrong version of Python or mixed up what version of Pytorch or something but now I keep having problems, that said I ran the script that is detailed in the following video, it is just one single copy/paste of the script into powershell, I ran it, it worked great but something at my end is screwing up, anyway check out this video search for, One-Click Whisper Install - Windows Install Script It's a One stop shop for whisper install
Yes, I should have mentioned that the process is the same in Windows if you have Python set up. You can also use WSL. However you have to deal with Windows. I've never had a good experience with Windows and Python, especially when working with AI/ML stuff.