Joint rnnt/ctc training

[iankur]

Signed-off-by: Ankur Kumar [email protected]

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

• Adds support to optionally train CTC decoder jointly with RNN-T model (encoder is shared)

Collection: [ASR]

Changelog

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

Usage

• You can potentially add a usage example below Need to add following flags to RNN-T training command and set D_MODEL to encoder output dim

++model.ctc.ctc_reduction=mean_batch \
++model.ctc.ctc_loss_weight=0.3 \
++model.ctc.decoder._target_=nemo.collections.asr.modules.ConvASRDecoder \
++model.ctc.decoder.feat_in=$D_MODEL \
++model.ctc.decoder.num_classes=-1 \
++model.ctc.decoder.vocabulary=[]

# Add a code snippet demonstrating how to use this 

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:

• [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.

Additional Information

• Related to # (issue)