bugbakery / bugbakery/transcribee

Whisper configuration

Open
#20 0 comments 1 reaction 0 assignees View on GitHub
discuss
Dominant language
TypeScript
Stars
515
Forks
39
Avg merge
19h 36m
Merged PRs (30d)
15

Description

Currently the parameters configuring whisper are hardcoded to be the same as the `whisper.cpp` cli.
This notably includes the sampling strategy and the maximum segment length.
Do we want to make this configurable?

Manual Experiments seem to indicate the `best_of` parameter of the `Greedy` sampling Strategy having a huge influence.

Interesting parameters:
- maximum segment length
- sampling strategy + configuration
- inital prompt
- ....

Contributor guide

Open the contributing guide

Research direction

Start by tracing how Whisper configuration is passed to the whisper.cpp CLI, focusing on the defaults for sampling strategy, best_of, maximum segment length, and initial prompt. Define which parameters must become configurable and what user-facing configuration and behavior would count as complete.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.