Streaming Sortformer release PR04: Adding functional tests for streaming sortformer

[tango4j]

What does this PR do ?

This PR is adding functional tests (CI tests) for inference and training.

Collection: [Note which collection this PR will affect]

ASR/speaker_tasks

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

• Adding these functional tests:

L2_Speaker_dev_run_EndtoEnd_Streaming_Speaker_Diarization_Sortformer.sh
L2_Speaker_dev_run_EndtoEnd_Streaming_Diarizer_Inference.sh

• Also adding streaming_sortformer_train.py

• You can potentially add a usage example below

# For evaluation of streaming speaker diarization
python $BASEPATH/neural_diarizer/e2e_diarize_speech.py \
    model_path=/path/to/diar_streaming_sortformer_4spk-v2.nemo \
    batch_size=1 \
    dataset_manifest=/path/to/diarization_manifest.json

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 NeMo ASR

Additional Information

• Related to # (issue)

[Copilot]

Pull Request Overview

This PR adds functional tests for the streaming Sortformer speaker diarization model, including both training and inference test scenarios. The purpose is to ensure the streaming Sortformer functionality works correctly in CI environments.

• Adds two functional test scripts for end-to-end streaming speaker diarization testing
• Introduces a new training script specifically for streaming Sortformer diarization
• Provides test coverage for both training and inference workflows

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
tests/functional_tests/L2_Speaker_dev_run_EndtoEnd_Streaming_Speaker_Diarization_Sortformer.sh	Functional test script for training streaming Sortformer with fast dev run
tests/functional_tests/L2_Speaker_dev_run_EndtoEnd_Streaming_Diarizer_Inference.sh	Functional test script for inference using pre-trained streaming Sortformer model
examples/speaker_tasks/diarization/neural_diarizer/streaming_sortformer_diar_train.py	Training script for streaming Sortformer diarization model

[ipmedenn]

LGTM