ml-explore / ml-explore/mlx-examples

Using fine tuned whisper models in MLX must support beam search

Open
#1,391 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9k
Forks
1.2k
PR merge metrics
No merged PRs in 30d

Description

The ability to specify the beam search size is very important for whisper-based models to achieve good accuracy, but it seems that MLX does not support it.

Please expand this capability of MLX.

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 locating the Whisper fine-tuning or inference entry point in the MLX examples and trace how decoding is configured. Done means fine-tuned Whisper models can accept and use a configurable beam-search size, with focused coverage if an existing test path is found.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.