Benchmark

VocalSound

A dataset for improving human vocal sounds recognition, containing over 21,000 crowdsourced recordings of laughter, sighs, coughs, throat clearing…

Modality
audio
Categories
audio
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen2.5-Omni-7BQwen0.9392025-03-27evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.