Remove the PnC flag from the ASR inference pipelines

[naymaraq]

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An outdated branch is never blocking the merge of a PR.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.

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

Collection: [ASR]

Changelog

Remove the PnC flag since external PnC is no longer used; rely on ASR output instead.

Summary

• Remove the enable_pnc flag from the streaming ASR inference pipeline — the per-request and global PnC on/off toggle is no longer needed since PnC output is now always preserved as-is from the ASR model
• Remove associated dead code
• Update all pipeline configs (YAML), pipeline implementations, request options, and the streaming tutorial notebook to reflect the removal
• Add functional tests for cache-aware pipelines
• Rename augment_with_default -> fill_defaults

Verification

Model: nvidia/nemotron-speech-streaming-en-0.6b

In main, enable_pnc=True is explicitly set. This branch removes enable_PnC flag. This comparison verifies that the change has no impact on WER.

Dataset	main	this PR	Diff
AMI	13.7544	13.7544	0.0000
Earnings22 Test	12.7078	12.7078	0.0000
Gigaspeech Test	9.7836	9.7836	0.0000
Librispeech Test Clean	2.3837	2.3837	0.0000
Librispeech Test Other	4.9110	4.9110	0.0000
Spgispeech Test	3.0050	3.0050	0.0000
Tedlium Test	3.4708	3.4708	0.0000
Voxpopuli Test	8.0605	8.0605	0.0000

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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

[github-actions]

[🤖]: Hi @naymaraq 👋,

We wanted to let you know that a CICD pipeline for this PR just finished successfully.

So it might be time to merge this PR or get some approvals.

[naymaraq]

/claude review

[arushidNV]

LGTM. Thanks!