jferments
jferments
Thanks! I will take a look at your source code for simpletuner, and see if that helps me understand how to do it. I'm still trying to wrap my head...
I really appreciate you taking the time to explain the reasoning behind this. There is not a lot of information about how aspect ratio bucketing works available online, so it...
I would be very interested to see this code as well! I am wanting to create some fine-tuned models, and it would be very helpful to see the original training...
I am also experiencing the same issue and am curious what I need to do to resolve.
Thanks, but I am attempting to transcribe from an ndarray containing audio recorded with sounddevice library. The audio is there, and I can play it back with sd.play() ... but...
> I'm curious about why do you want to do this instead of using already done solutions like SimpleTuner or sd-scripts, and if you want a gui you can use...
Do you have links to tickets where they've rejected this idea? I didn't see any for it when I searched
Yes, I ended up using [YoloV11](https://docs.ultralytics.com/models/yolo11/#overview) for object detection / masking, followed by [simple-lama-inpainting](https://github.com/enesmsahin/simple-lama-inpainting) for object removal. You can see how I combined the two of them to perform watermark...