- cross-posted to:
- [email protected]
- cross-posted to:
- [email protected]
wicked list thanks
I’d never heard of Subsync before and I’ve just spent the last two hours fixing so many subtitles.
I’d had good results using SubtitleEdit to offset subs and set sync points before, but this tool is on another level. I might actually need to go back and use it to polish up a few subtitles that I got mostly right, but not quite.
The panoramic tool sounds great, although I mostly get pretty good results with the photomerger in Photoshop, I’m going to try this tomorrow on some panoramas I had trouble with. Oh and a pretty cool tool I heard rarely mentioned is: Zero shot Voice cloning and generation using this fork of tortoise tts and the model trained by this smart guy Nanonomad for multi language inference. Great for adding quick voice-over and prototypes. Runs alright on my old Notebook (2x gtx1080m).
Decent list, but is it just me, or does all of it sound like common knowledge?
I’ve used Spleeter CLI quite often, but I’ve also heard that there are better, open-source models out there that outperform the one that is used in Spleeter, unfortunately, neither is the pre-trained model, nor the project repo available - just an open-access paper.
This page also missed out on essential apps like Tesseract OCR which is a must-have.
Could be common knowledge to some. But since it’s posted in a general technology community instead of an AI-focused one I’m sure there will be users who aren’t as much in the loop.