Common Voice 15

Multilingual
audio
+
+
+
+
About

Common Voice 15 is a speech recognition and processing benchmark based on Mozilla's crowdsourced multilingual speech dataset. This benchmark evaluates AI models' ability to understand and process speech across diverse languages, accents, and speaker demographics. Common Voice 15 provides comprehensive assessment of speech recognition capabilities, linguistic diversity handling, and cross-cultural voice understanding in multilingual contexts.

+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score100
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers

Score Distribution

1 models
Top Score
7.6%
Average Score
7.6%
High Performers (80%+)
0

Top Organizations

#1Alibaba Cloud / Qwen Team
1 model
7.6%
+
+
+
+
Leaderboard
1 models ranked by performance on Common Voice 15
LicenseLinks
Mar 27, 2025
Apache 2.0
7.6%
+
+
+
+
Resources