New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Request: provide Openvino models #1893
Comments
I have converted the models to OPENVINO and strive to publish them on Huggingface soon but for now, they are available through the following IPFS folders. Every model includes the original GGML bundle accompanied by converted OPENVINO encoder files. The original pretrained OpenAI models and Large models will be added soon. The English-only models (
|
Thanks for taking on generating the OpenVINO files and sharing them. I am not having any luck downloading the files via Kubo or the IPFS Desktop application. This is the first time I have used IPFS, so I very well might be missing something. |
@BBBalls there could be some problems while the data are coming over the network. I set up the providing, so in a few days everything should be fine |
Added Large models |
@twdragon Thanks again. |
the models are added to Huggingface: https://huggingface.co/twdragon/whisper.cpp-openvino |
I have been able to appreciate significant performance increases utilizing Openvino for the models that I can covert, but my laptop does not seem to have enough ram (16 GB) to convert the large models.
If it is technically possible, it would be great if Openvino models were provided on HuggingFace, like how the CoreML models are made available.
Thanks
The text was updated successfully, but these errors were encountered: