Skip to content

fix(timestamp): keep a timestamp for every token when the last frame is heavy - #3935

Merged
LauraGPT merged 1 commit into
modelscope:mainfrom
prassu017:fix/3934-owed-fire-timestamps
Nov 22, 2026
Merged

LauraGPT merged 1 commit into
modelscope:mainfrom
prassu017:fix/3934-owed-fire-timestamps

Conversation

@prassu017

Copy link
Copy Markdown
Contributor

Summary

A short segment whose last frame carries most of the weight could come back with fewer timestamps than tokens, and since 1.4.19 that fails the whole request. The missing ones are now spread over what's left of the segment, so every token gets a time.

Fixes #3934

Type of change

  • Bug fix
  • Documentation
  • Example or demo
  • Runtime or deployment
  • Benchmark or evaluation
  • Model/training change

Validation

The three new cases (one uses the values captured in the issue) fail on main and pass here, along with the existing timestamp and sentence postprocess tests. I also compared old and new on 5,000 random inputs: nothing changed where the old code already timed every token. Not run with real model weights.

  • compileall over funasr, examples and tests
  • Docs or links checked
  • Runtime/deployment command tested

User impact

Long recordings transcribed with VAD no longer fail because of one tiny segment.

Notes for reviewers

The recovered timestamps are an even split, so they're approximate when more than one token lands in that last frame. I left the ONNX runtime's copy alone.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

ts_prediction_lfr6_standard drops a token timestamp when CIF must fire twice in one frame (ValueError in sentence_postprocess since 1.4.19)

2 participants