Add CHAT (Chunk-wise Attention Transducer) model support

[hainan-xv]

What does this PR do ?

Add support for CHAT (Chunk-wise Attention Transducer) model.

Collection: [Note which collection this PR will affect]

ASR

Changelog

Introduce CHAT model architecture for streaming ASR with cross-attention in the transducer joint network. Key changes:

• Add JointWithAttention module with multi-head cross-attention between decoder and encoder representations in the joint network (rnnt.py)
• Add ChatRNNTDecoding and streaming/chunked inference support with chunk_frame_lengths propagation through the decoding pipeline

Important

The Update branch button must only be pressed in very rare occassions.
An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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