Kadir Nar
Kadir Nar
@rafstahelin I tested CLIPSeg + LaMa model. CLIP model doesn't detect text well. That's why the output is bad. You can use VLM models for text detection. But vlm models...
This can be done using this library. I want to add generative ai models to this library. Github: https://github.com/fcakyon/craft-text-detector
> > This can be done using this library. I want to add generative ai models to this library. > > Github: https://github.com/fcakyon/craft-text-detector > > Would love to test your...
> Hey @rafstahelin and @kadirnar > > We made a couple of comfy custom nodes, see #421. We only support our new [Box Segmenter](https://huggingface.co/spaces/finegrain/finegrain-object-cutter) at the moment, but we're thinking...
Didn't download the mp3 file. Is the link correct?
Sometimes there is a problem while downloading. That's why you have to try again and again.
Can you give the path of the .mp3 file to the audio_pah variable? Because it cannot read the audio file. It returns to None.
Which pipeline are you using?
I will add lang parameter support tomorrow.
What code are you using? Which GPU?