Audio Generation on AudioCaps

Metric: CLAP_MS (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	CLAP_MS▼	Extra Data	Paper	Date↕	Code
1	GenAu-Large	0.668	No	Taming Data and Transformers for Audio Generation	2024-06-27	Code
2	ETTA-FT-AC-100k	0.43	No	ETTA: Elucidating the Design Space of Text-to-Au...	2024-12-26	Code
3	ETTA	0.43	No	ETTA: Elucidating the Design Space of Text-to-Au...	2024-12-26	Code
4	AudioLDM2-large	0.37	No	AudioLDM 2: Learning Holistic Audio Generation w...	2023-08-10	Code
5	Stable Audio Open	0.34	No	Stable Audio Open	2024-07-19	Code

#1GenAu-LargeSOTA
0.668
CLAP_MS· 2024-06-27
Taming Data and Transformers for Audio Generation Code
#2ETTA-FT-AC-100k
0.43
CLAP_MS· 2024-12-26
ETTA: Elucidating the Design Space of Text-to-Audio Models Code
#3ETTA
0.43
CLAP_MS· 2024-12-26
ETTA: Elucidating the Design Space of Text-to-Audio Models Code
#4AudioLDM2-largeSOTA
0.37
CLAP_MS· 2023-08-10
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining Code
#5Stable Audio Open
0.34
CLAP_MS· 2024-07-19
Stable Audio Open Code