Task: DL model training/finetuning and testing for audio classification

[fabiocat93]

Description

Implement a pipeline for deep learning model training, finetuning, and testing for audio classification tasks

Tasks

• Data loading
• Training/finetuning
• Testing

Freeform Notes

No response

[wilke0818]

Curious how we would even go about testing such a pipeline? Seems difficult to unit test though I have code that we both believe does this.

[fabiocat93]

Curious how we would even go about testing such a pipeline? Seems difficult to unit test though I have code that we both believe does this.

I would split the process in sub-tasks and test those first

[wilke0818]

I guess I was curious if you knew of good examples of testing tasks like finetuning? This is a later issue but it is one of those tasks that seems computationally infeasible to have a unit test run on for every push.

[fabiocat93]

I guess I was curious if you knew of good examples of testing tasks like finetuning? This is a later issue but it is one of those tasks that seems computationally infeasible to have a unit test run on for every push.

We can do speech emotion recognition, speaker identification, or sex prediction in our case studies.
Agree that not everything can be tested as a unit test