VBdiarization
czecze123 opened this issue · 4 comments
-
I want to ask the logic problem of speech segmentation. After the environment is set up, the program will run
onnxruntime.capi.onnxruntime_ pybind11_ state.InvalidArgument : [ONNXRuntimeError] : 2 index: 2 Got: 121 Expected: 100 Please fix either the inputs or the model.
Where there is an error and how to correct it? -
The input voice signals list_ spk.scp In file Fe_ 03_ 00001-a 1 fe_ 03_ 00001-b 1 has only one person, why do we need to implement speaker segmentation?
Thank you!
By the way , i cannot contact you by e-mail.
Hi,
- Please try
pip install onnxruntime==0.3.0
as specified inrequirements.txt
- Yeah, it is just some prehistoric example. I will probably substitute it with something different in the future.
sorry about that, I made some mistake in merging or something, please check requirements.txt
now
sorry about that, I made some mistake in merging or something, please check
requirements.txt
now
thanks!