Refactor dataset class, drop dependencies and update models

[ben9809]

This PR introduces new changes regarding a specific dataset and SNNTorchModel

1. Code on the WISDM dataset class has been refactored to match the default code style of other dataset classes' implementation. This allow as to drop some dependencies like gdown and pytorch-lightning.

2. Apart from the two dropped packages, some others have been dropped: librosa and tonic.

3. Add documentation to SNNTorchModel and refactor code to avoid output tensor shape mismatch

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 78.38%. Comparing base (f203109) to head (11d0bf7).

Additional details and impacted files

@@            Coverage Diff             @@
##              dev     #277      +/-   ##
==========================================
+ Coverage   78.14%   78.38%   +0.23%     
==========================================
  Files          44       44              
  Lines         842      842              
  Branches      123      123              
==========================================
+ Hits          658      660       +2     
+ Misses        134      132       -2     
  Partials       50       50              

Flag	Coverage Δ
unittests	78.38% <100.00%> (+0.23%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.