angrysword

Thanks so much for this. if you can work out a simple image generation as well, that will be wonderful. Mingpt have this function, prefer more mature one like put...

how to infer image of a segmentation or depth like the demo

7

have not find an easy way to do that. managed to get features. `import torch from PIL import Image import torchvision.transforms as T import hubconf dinov2_vits14 = hubconf.dinov2_vits14() image_transforms =...

I am training indoor scene, training takes forever

6

Thanks for very cool demo. I am training the indoor scene with 1100 frame in the dataset. with rtx 4090. 3dscene dir is just indoor 1100 images. did I do...

When use speech to text inference, how to keep the src_lang same as tgt_lang

1

Many real world speed may include two or more language, like the people who speak Japanese, may some words have to use English. when we do transcribe, we like to...

do not waste your time to try this. simply put, not works. refer this as well 'Nothing alike #43'

2

Perfect demo, waste time to try. I waste 1 to 2 hours to try, no luck. then I found #43. others face the same

It just works. it is forever free, it is offline accessible. if a lot of people install it, i will update more feature. with a local llm model to summarize,...