Audio Captioning

Generating text descriptions of audio content.

Datasets

Results

spider

Canonical metric

Canonical Benchmark

AudioCaps

Audio generation quality evaluated on AudioCaps captions

Primary metric: spider

Leading models on AudioCaps.

Rank	Model	fad	Year	Source
1	AudioLDM	4.48	2023	paper
2	AudioLDM 2-Full-Large	1.86	2024	paper
3	AudioLDM 2-Full	1.78	2024	paper
4	TANGO	1.73	2023	paper
5	AudioLDM 2-AC-Large	1.42	2024	paper

1 dataset tracked for this task.

Other tasks in Audio.