Fixed chokepoint in diarization for longer audios

[AatikaNazneen]

What does this PR do ?

Even after addition of long form clustering feature, the code was failing because get_argmin_mat acted as a chokepoint and consumed too much memory for a mathematical operation that was not that complex. The tiling function ended up creating n^2 size matrices. The current function gives a drastic change in memory consumption with minimal change in running time.
Fixes the problem described in OOM Clustering Bug
Collection: asr

Changelog

• Add specific line by line info of high level changes in this PR.

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

GitHub Actions CI

The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.

The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you add or update any necessary documentation?
• Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
  • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

• New Feature
• Bugfix
• Documentation

If you haven't finished some of the above items you can still open "Draft" PR.

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

• Related to # (issue)

[AatikaNazneen]

I will modify the code so that all the test cases pass soon.

[tango4j]

Thank you for suggesting this idea.
Currently I don't have bandwidth to test this so let me check on this as soon as I have bandwidth to take care of this.
This needs to be tested with long-form and short-form audio clustering.

[github-actions]

This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days.