ashrafee-dev / ashrafee-dev/scamshield-api

Load the Whisper model lazily

Open
#47 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

good first issue
Dominant language
Python
Stars
3
Forks
10
Avg merge
14h 44m
Merged PRs (30d)
9

Description

Goal

Avoid loading the large Whisper turbo model whenever an import does not need audio transcription.

Acceptance criteria

  • Move model initialization behind a lazy accessor or equivalent.
  • Preserve existing transcription behavior.
  • Ensure tests that do not exercise audio can import the app without downloading/loading Whisper.

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

Find the Whisper turbo model initialization and the application import paths that currently trigger it. Run the tests that do not exercise audio, then verify they import without loading or downloading Whisper while transcription behavior remains unchanged.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, machine-learning
Issue type
Refactor
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
70/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.