LAION-AI / LAION-AI/CLAP

Text embedding code failing for single prompt

Open
#85 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
213
PR merge metrics
No merged PRs in 30d

Description

When I try to use clap_model.get_text_embedding() on an array with a single prompt in it, the call fails with an error in the Roberta tokenizer. It seems that it's confused about the shape of the array unless there's more than one element in it.

File ".../transformers/models/roberta/modeling_roberta.py", line 802, in forward
batch_size, seq_length = input_shape
ValueError: not enough values to unpack (expected 2, got 1)

Contributor guide

No contributing guide indexed for this repository

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 at clap_model.get_text_embedding() and reproduce the failure with an array containing one prompt. Then inspect the Roberta tokenizer/model path indicated by transformers/models/roberta/modeling_roberta.py:802. Done means the single-prompt call completes without the input-shape error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.