Speech to text using whisper timestamped and gradio

Intermediate
1

I am working on a speech to text app using whisper-timestamped and gradio. When I started this project, this all worked fine. Within the last week I have started getting this error:
ValueError: This ORT build has [‘AzureExecutionProvider’, ‘CPUExecutionProvider’] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession.
And now I am trying to figure out how to resolve this. Any insights or suggestions would be greatly appreciated.

2

I have worked through that error, but now I am getting this:
TypeError: Unable to load from type ‘<class ‘whisper.model.Whisper’>’
The main thing that I am not understanding is why did my app work before, but now I am having all of these issues.

3

Hi @michaelschell. I’m seeing the same error related to the ORT build. How did you manage to fix the problem?