[ASR]:fixed augmentor arguments for transcribe functionality of Hybrid CTC-RNNT model

[KunalDhawan]

What does this PR do ?

Fixes issues in nemo/collections/asr/models/hybrid_rnnt_ctc_models.py regarding Augmentor parameters to enable transcribe functionality for hybrid RNNT-CTC models

Collection: [ASR]

Changelog

• in the function transcribe() of class EncDecHybridRNNTCTCModel, added
  • augmentor argument in function call (line 103)
  • augmentor argument in the config for calling _setup_transcribe_dataloader() (line 179)

Usage

• You can potentially add a usage example below

python  NeMo/examples/asr/transcribe_speech.py \
    model_path="path to hybrid model" \
    pretrained_name="name of hybrid model from NGC directory" \
    audio_dir="path to folder of audio files" \
    dataset_manifest="path to manifest" \
    output_filename="output filename" \
    batch_size=32 \
    compute_timestamps=False \
    compute_langs=False \
    cuda=0 \
    amp=True \
    append_pred=False \
    pred_name_postfix="another model name for output filename, if required"

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)