OpenNMT / OpenNMT/CTranslate2

Whisper model returns empty logits array

Open
#1,822 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

Hello, when enabling return_logits_vocab in whisper, an empty array is returned, this is reproducible with any input
result[0].logits[0][0].__array_interface__:

{'shape': (), 'typestr': '<f4', 'data': (0, False), 'version': 3}

Using CT2 4.5.0

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the issue with Whisper using CT2 4.5.0 and the return_logits_vocab option, then inspect the implementation and tests for result[0].logits[0][0]. Done means the returned logits array contains the expected values for reproducible Whisper inputs instead of an empty array.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.