Prince Canuma
Prince Canuma
Thanks a lot! Will merge as soon as the tests clear.
Maybe related with removal of load from AutoConfig. I will check and comeback to you. Meanwhile test out updating your Transformers
The issue is that DeepSeekOCR is a trained and behaves as a traditional OCR model. It requires specific prompts and doesn't respond well to prompts outside the ones it was...
Or, if this input worked before please let me know at which version and I will reproduce the issue
Awesome, This is on backlog!
Well done @DePasqualeOrg! > @Blaizzy, we could also download the Kokoro [voices](https://huggingface.co/mlx-community/Kokoro-82M-bf16/tree/main/voices) from Hugging Face instead of bundling these heavy JSON files if they are uploaded as .safetensors instead of...
> For LLMs in Swift we currently have a repo called mlx-swift-lm. Following this pattern, we could name the Swift package repo mlx-swift-audio. Interesting proposal. I don't have strong ideas...
> The espeak-ng organization already has this Swift package, which I'm using in this PR: https://github.com/espeak-ng/espeak-ng-spm @rudrankriyam what are your thoughts on this?
@rudrankriyam could you handle the voices? If you come across any issues let me know.
It's stable @DePasqualeOrg 👌🏽 v0.3.0 fixes all Gemma3n bugs