ggml-org/whisper.cpp

Add option to extend Confidence color-coding to CSV or some other output file format

Open

#427 opened on Jan 19, 2023

View on GitHub
 (5 comments) (17 reactions) (0 assignees)C++ (5,535 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (49,693 stars)
PR merge metrics
 (Avg merge 5d 20h) (36 merged PRs in 30d)

Description

So for spot checking long transcriptions, it would be helpful to have the confidence score output to some file.. either as an extra column in the CSV or maybe some metadata in VTT or even it's own log or something.

Thanks! This is amazing work!

Contributor guide

Research direction
Implement an option in whisper.cpp to output confidence scores for each segment, similar to the color coding in terminal output. Add a new flag like ' output confidence' that appends a confidence column to CSV or includes metadata in VTT. Study the existing output code in examples/main.cpp or similar.
Tech stack
cpp
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70