Prince Canuma comments

Results 572 comments of


                                            Prince Canuma

Should Sampling Rate be Automatically Set with Default Sampling Rate Each Model Uses?

Thanks for opening this issue! Yes, I agree. It's one of the things I kept in mind coming into v0.2.0 since we now have lots of models with varying sampling...

how to fix "cannot import name 'get_stt_model' from 'fastrtc'"

do you have fastrtc installed?

Enhance Visualizer

Hey @VxASI Thank you very much for this beautiful visualizer, really love the concept! Could you have as an option users can toggle accross this one and the old one?

API choice feedback

Hey Zach Thanks for the awesome feedback! Indeed we need more detailed errors for voice cloning and default voices. Will work on it. Regarding the second point. For voice cloning...

Support for Video with Qwen2-VL

Hey @tmoroney Indeed, it's a cool feature of Qwen2-VL. I will work on adding it after #41 and Molmo port. Could you share a little bit more about your project?

Support for Video with Qwen2-VL

I got multi-image support working which is pretty close to video. From here to video it’s pretty close but I want to make the API seamless for all models, that’s...

Support for Video with Qwen2-VL

Thanks guys! There is a PR for video support #97 it works but needs a bit of polishing I will do that and merge it over the weekend.

Support for Video with Qwen2-VL

Could you elaborate?

ValueError: [conv] Expect the input channels in the input and weight array to match

Hey @arogister I will fix the readme examples later today For now here is the solution: https://github.com/Blaizzy/mlx-embeddings/issues/18#issuecomment-2777111054

Make it possible to load siglip models from local files

Hey @maxlund Thanks for the PR! The context is that for certain models they don't supply the patch and img size on the `config.json`, I can only find it in...