Use a local model to cleanup the speech

Open
  • Is something wrong?
#208 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Active
Tech stack
swift
Domain
ai, desktop

Research direction

Start by reading the app’s existing speech cleanup and model integration entry points; the issue does not name any files or tests. Compare the built-in macOS model with the suggested local model options and determine how they should fit into SpeakType. Done means speech artifacts are cleaned up and spoken content is structured, but the issue leaves the desired model and behavior open.

Written by the indexing model from the issue text.

Description

enhancement
What are you trying to do?

Currently the MacOS has a built in lightweight and optimized language model It could be used to clean up language artifacts and spoken parts and to give it a structure. There should be a possibility to integrate this into speaktype. Alternatively, if there is a model running through Lama, VLM, whatever, it should be able to use and leverage that as well.

What would you like SpeakType to do?

To clean up the artifacts from spoken words and speech more efficiently and in line with how the platform for macOS actually works.

How do you work around it today?

I don't. And it's annoying.

Dominant language
Swift
Stars
540
Forks
74
No merged PRs in 30d

Getting set up

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.

More from karansinghgit/speaktype

All issues in karansinghgit/speaktype

Similar issues

More Swift issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.