Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added model config params for Canary-1B-Flash, Canary-180M-Flash models #12588

Merged
merged 4 commits into from
Mar 15, 2025

Conversation

KunalDhawan
Copy link
Collaborator

Important

The Update branch button must only be pressed in very rare occassions.
An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.

What does this PR do ?

Adds model config param table to asr/conf/speech_multitask/fast-conformer_aed.yaml to cover Canary-1B-Flash and Canary-180M-Flash models.

Collection: ASR

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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 # (issue)

Sorry, something went wrong.

nithinraok
nithinraok previously approved these changes Mar 13, 2025
Copy link
Collaborator

@nithinraok nithinraok left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

minor comment. LGTM

@@ -7,6 +7,15 @@
# One extra (linear projection) layer is added between FastConformer encoder and Transformer decoder if they have different hidden sizes
# It is recommended to initialize FastConformer with ASR/SSL pre-trained encoder for better accuracy and faster convergence

# Canary model family
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a sample training manifest json line to the top of the file

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Something like this?
{"audio_filepath": "/path/to/audio/file.wav", "duration": 6.192, "text": "Text spoken in the audio.", "source_lang": "en", "target_lang": "en", "taskname": "asr", "pnc": "yes"}

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes

nithinraok
nithinraok previously approved these changes Mar 13, 2025
Signed-off-by: Kunal Dhawan <kunaldhawan97@gmail.com>
Signed-off-by: Kunal Dhawan <kunaldhawan97@gmail.com>
Signed-off-by: Kunal Dhawan <kunaldhawan97@gmail.com>
@KunalDhawan KunalDhawan force-pushed the add_canary_flash_config branch from 5f266b9 to e0f4402 Compare March 14, 2025 06:21
@ko3n1g ko3n1g added Run CICD and removed Run CICD labels Mar 14, 2025
Signed-off-by: Kunal Dhawan <kunaldhawan97@gmail.com>
@KunalDhawan
Copy link
Collaborator Author

@ko3n1g could you please review, all CICD tests passed

@KunalDhawan KunalDhawan merged commit 9619590 into NVIDIA:main Mar 15, 2025
361 checks passed
@KunalDhawan KunalDhawan deleted the add_canary_flash_config branch March 15, 2025 00:16
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @KunalDhawan (cc @pzelasko )

Can we remove these? These are not relevant for canary-flash and we end up passing the same path as argument here and later under model.tokenizers

  model_dir: ???
  tokens: ["translate", "transcribe", "en", "es", "de", "fr"]
  force_rebuild: False  # Set to True to build new tokenizer each time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants