Review and test classification

[ibevers]

This PR is for reviewing, updating, and adding tests to the classification.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 9.09091% with 40 lines in your changes missing coverage. Please review.

Project coverage is 62.33%. Comparing base (f3c595f) to head (9fab779).
Report is 28 commits behind head on main.

Files	Patch %	Lines
src/tests/audio/tasks/classification_test.py	5.40%	35 Missing ⚠️
...tasks/classification/speech_emotion_recognition.py	28.57%	5 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #106      +/-   ##
==========================================
- Coverage   63.04%   62.33%   -0.72%     
==========================================
  Files          63       65       +2     
  Lines        2073     2156      +83     
==========================================
+ Hits         1307     1344      +37     
- Misses        766      812      +46     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[wilke0818]

I believe this as is might fail with GPU models but can test in colab later. Have been making some changes to these functions in jordan_060 but can definitely merge some of these changes together. also I think batching should possibly be done slightly differently but this is likely a larger conversation with @fabiocat93 next week on how to incorporate best with Pydra. otherwise looks good

[ibevers]

Ah, okay, we'll discuss next week then

[fabiocat93]

@ibevers i see you self-assigned the review of audio classification and started working on it. is there anything else that you think should be done in terms of documentation, tutorial, testing, code optimization?

[ibevers]

@ibevers i see you self-assigned the review of audio classification and started working on it. is there anything else that you think should be done in terms of documentation, tutorial, testing, code optimization?

@fabiocat93 @wilke0818 We still need to discuss the batching approach here. Also, this needs a tutorial.

To-dos:

• Determine whether batching approach makes sense, change if necessary, and test
• Add tutorial

[fabiocat93]

@wilke0818 @ibevers how do you intend to proceed with this? is there any progress update?

[wilke0818]

we never really discussed batching so I don't have any updates. I have a tutorial I can upload at some point for speech emotion recognition

[fabiocat93]

we never really discussed batching so I don't have any updates. I have a tutorial I can upload at some point for speech emotion recognition

would be great. thanks! at least to have it there if someone needs it (even if not optimized)