improve canary performance on short audio

[nithinraok]

What does this PR do ?

Fixes: #15305

Fix transcription and timestamps prediction for shorter sequences with canary models when using torch tensor/ numpy array as input

Collection: ASR

Changelog

• Add min padding of 1sec when using tensor/array as input
• Pad on both sides (default used in canary models)

Usage

from nemo.collections.asr.models import EncDecMultiTaskModel
model = EncDecMultiTaskModel.from_pretrained("nvidia/canary-1b-v2")

import librosa
audio, sr = librosa.load('<path to audio>', sr=16000)

hypotheses = model.transcribe(
    audio=audio,
    source_lang='fr', target_lang='fr', timestamps=True,
    batch_size=1,
    return_hypotheses=True,
)
print(hypotheses)

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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 Getting timestamps using NeMo tensor loading #15305

[github-actions]

[🤖]: Hi @nithinraok 👋,

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.

//cc @chtruong814 @ko3n1g @pablo-garay @thomasdhc

[pzelasko]

good catch, LGTM