search

sensein / senselab

SenseLab is a Python package that simplifies building pipelines for biometric (e.g. speech, voice, video, etc) analysis.
https://github.com/sensein/senselab
Apache License 2.0
6 stars 3 forks source link

Task: DL model training/finetuning and testing for audio classification #28

Open fabiocat93 opened 1 month ago

fabiocat93 commented 1 month ago

Description

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

Tasks

Freeform Notes

No response

wilke0818 commented 1 month ago

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 commented 1 month ago

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 commented 1 month ago

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 commented 1 month ago

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