Hugging Face's logo

Spaces:
sarulab-speech
/
MSR-UTMOS
Running on Zero

App Files Community
1

Apply for community grant: Academic project (gpu)

#2
by Wataru - opened
Discussion
Wataru
 SaruLab Speech group org

This is a demo for automatic quality prediction of speech. Which we will be releasing preprint shortly.
I'd like to have GPU for faster inference
hysts

Hi @Wataru , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
hysts

BTW, looks like you added a model file in your Space repo, but could you create a separate model repo and download the model from it at startup? It's not recommended to add models in Space repo. You can use the huggingface-hub library. (docs)
Wataru
 SaruLab Speech group org

Thank you so much! for the prompt response!
I will move the checkpoint to seperate model repo as you suggested.

Wataru changed discussion status to closed

Sign up or log in to comment