[Fix] Discriminator update in AudioCodecModel

[anteju]

What does this PR do ?

This change removes random selection when deciding to update the discriminator in the AudioCodecModel.

Collection: TTS

Changelog

• Instead of using a random number, update the discriminator disc_updates_per_period times for every disc_update_period batches
  • This fixes an issue when training with multiple GPUs
• Added logging in audio_codec.py training script

Usage

N/A

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)

[rlangman]

LGTM