Hosted inference API: Pipeline cannot infer suitable model classes

🤗Hub
1

When I try to use the inference pipeline widget for my public project, I got this error.
image

But the pipeline works locally

2

hi @KELONMYOSA ,

does your model work when you run with transformers?

from transformers.pipelines import pipeline
pipe = pipeline(model="KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru", trust_remote_code=True)
result = pipe("speech.wav")
print(result)

Could you try update the model card and add the correct tags?

tags:
  - audio
  - audio-classification
3

Hi, @radames

  • Yes, everything works when I run it locally using transformers as specified in readme (pipeline and automodel)
  • I have updated the model card
4

This issue has been popping up on a bunch of different models and endpoints actually. I think there is a deeper issue at play.