add longform chunk inference #14864
Open
add longform chunk inference #14864
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: nithinraok <[email protected]>
Signed-off-by: nithinraok <[email protected]>
pyf98
reviewed
Oct 3, 2025
| model_kwargs['cfg']['pretrained_weights'] = False | ||
| # When loading from HF checkpoint, set init_from_path to the HF checkpoint directory | ||
| # so it can load the model weights from the correct location. | ||
| if 'init_from_path' in model_kwargs['cfg']: |
There was a problem hiding this comment.
init_from_path is used to load a checkpoint from a previous stage.
In Stage 1, this argument is not set.
In Stage 2, it points to the final HF checkpoint from Stage 1.
When loading the final checkpoint after Stage 2, perhaps we do not need init_from_path, assuming the HF checkpoint saves everything.
pyf98
reviewed
Oct 3, 2025
Comment on lines
+532
to
+535
| asr_tokens_chunk = [ | ||
| torch.as_tensor(self.tokenizer.text_to_ids(f">> {hyp.text} <<" if hyp.text else ">> <<")) | ||
| for hyp in asr_hyps_chunk | ||
| ] |
There was a problem hiding this comment.
">>" and "<<" are applied at the very beginning and end of the ASR transcript.
For short audio, the final "audio" embedding looks like:
{audio_features}>> {asr_hyp} <<
I guess we can do the same for long audio:
{audio_features1}{audio_features2}>> {asr_hyp1} {asr_hyp2} <<
But here it seems ">>" and "<<" are added for each chunk instead
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Important
The
Update branchbutton 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 ?
Add support for inference for longer audio samples by chunking them into 10 min segments
Collection: SpeechLM2
Changelog
Usage
# Add a code snippet demonstrating how to use thisGitHub 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:
PR Type:
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