ggml-org/whisper.cpp

tests : add WER benchmarks

Open

#2,454 opened on Oct 5, 2024

View on GitHubContributor guide
 (26 comments) (0 reactions) (0 assignees)C++ (6,072 forks)batch import
help wantedhigh priorityresearch🔬roadmap

Repository metrics

Stars
 (52,942 stars)
PR merge metrics
 (Avg merge 5d 20h) (36 merged PRs in 30d)

Description

It would be nice to start measuring the word error rate (WER) of whisper.cpp across some representative dataset:

  • short audio
  • long audio
  • english
  • non-english
  • etc.

This will help us catch regressions in the future. I'm not familiar with what is typically used for TTS WER benchmarks, so looking for help from the community.

Contributor guide

Research direction
Look at existing WER calculation scripts and identify suitable datasets for English and non English, short and long audio. Check whisper.cpp's model output format for consistency.
Tech stack
cpp
Domain
testing qaai
Issue type
Test
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++Speech Recognition BasicsDataset Handling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
55