Bug fix for Issue #4059, word time stamps for single word cases

[tango4j]

Signed-off-by: Taejin Park [email protected]

What does this PR do ?

This PR fixes the bug reported in Issue #4059. Before this fix, QuartzNet ASR Model could not generate word timestamps for an utterance with a single word.

Collection: [Note which collection this PR will affect]

ASR

Changelog

• Function named get_word_ts_from_spaces() has been changed to handle the cases where there is only one word in the decoded output.
• Few changes in docstrings.

Usage

Please refer to README

python offline_diarization_with_asr.py \
    diarizer.manifest_filepath=<path to manifest file> \
    diarizer.out_dir='demo_asr_output' \
    diarizer.speaker_embeddings.model_path=<pretrained modelname or path to .nemo> \
    diarizer.asr.model_path=<pretrained modelname or path to .nemo> \
    diarizer.asr.parameters.asr_based_vad=True

Before your PR is "Ready for review"

Pre checks:

• [ x] 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
• [x] 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.