[ASR] Add pretrained ASR models for Croatian

[anteju]

Signed-off-by: Ante Jukić [email protected]

What does this PR do ?

This PR adds pre-trained models for Croatian.

Collection: [ASR]

Changelog

• updated PretrainedModelInfo and docs
• minor (cosmetic) modifications to checkpoint_averaging.py

Usage

Tested with the following

from nemo.collections.asr.models import ASRModel

for type in ['ctc', 'transducer']:
    model = ASRModel.from_pretrained(f'stt_hr_conformer_{type}_large', map_location='cpu')

    print(f'\nmodel_{type}.summarize()')
    print(model.summarize())
    print()

Pretrained models downloaded from NGC.

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?
• [x] 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:

• [x] 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.

[lgtm-com[bot]]

This pull request introduces 2 alerts when merging 452f18ab935c48a8ec7ad68d6b1c2092cd3a9a56 into 816ffda9f83739c92351486bb75b0c01ea4c8cb5 - view on LGTM.com

new alerts:

• 2 for Variable defined multiple times