[KongchangAI]
BenchmarkCommon Voice 27.0

Common Voice

A multilingual speech dataset crowdsourced by the Mozilla community, used for speech recognition training and evaluation, containing diverse recording conditions.

Timeline (last 90 days)

Nov 17

Marimba wins in binary term detection on Common Voice and FLEURS.

Unverified50%
Nov 3

On both the FLEURS and Common Voice datasets, ufakzeka-kulak's WER is lower than Whisper base and Whisper small, and the paired confidence intervals are entirely below zero, so the performance advantage is statistically significant.

Unverified50%
Nov 3

WER on FLEURS and Common Voice cannot be directly compared because the text normalization rules and speaker distributions differ.

Unverified50%

All Facts (3)

Source Articles