Skip to content

include text-only into fprop of training and eval; TODO: text-only inference#2

Merged
pzelasko merged 1 commit intopzelasko:canary_speechllm1_cross_t5_pr3from
zhehuaichen:canary_speechllm1_speech_text_lhotse
May 9, 2024
Merged

include text-only into fprop of training and eval; TODO: text-only inference#2
pzelasko merged 1 commit intopzelasko:canary_speechllm1_cross_t5_pr3from
zhehuaichen:canary_speechllm1_speech_text_lhotse

Conversation

@zhehuaichen
Copy link

What does this PR do ?

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

Collection: [Note which collection this PR will affect]

Changelog

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

Usage

  • You can potentially add a usage example below
# Add a code snippet demonstrating how to use this 

Jenkins CI

To run Jenkins, a NeMo User with write access must comment jenkins on the PR.

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)

predict

Signed-off-by: zhehuaichen <dian.chenzhehuai@gmail.com>
"""
Used to get LLM predictions for validation and test steps based on the given inference config.
"""
# TODO: we expect only one modality in each batch of inference. In lhotse, can we specify a list of datasets which only have one modality either audio-text or text-only?
Copy link
Owner

Choose a reason for hiding this comment

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

Yes, we can keep text-text and audio-text datasets separate for validation/test

Copy link
Owner

@pzelasko pzelasko left a comment

Choose a reason for hiding this comment

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

looking good

@pzelasko pzelasko merged commit d40a430 into pzelasko:canary_speechllm1_cross_t5_pr3 May 9, 2024
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.

2 participants

Comments