Group-residual vector quantizer

[anteju]

What does this PR do ?

This PR adds group-residual vector quantizer as in http://arxiv.org/abs/2305.02765

Collection: TTS

Changelog

• Added group-RVQ
• Added unit tests for RVQ

Usage

To use, add the following in the config file

  vector_quantizer:
    _target_: nemo.collections.tts.modules.encodec_modules.GroupResidualVectorQuantizer
    num_codebooks: 4 # total number of codebooks
    num_groups: 2 # number of groups
    codebook_dim: 128 # dimension of the audio encoder output

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)

[nithinraok]

lgtm

[rlangman]

LGTM