Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
Open paper
Benchmark
Model
Rank
Results
text-to-audio-retrieval-on-clotho
PaSST–RoBERTa & GPT-augment
#4
R@1: 26.07
R@5: 55.27
R@10: 69.30
mAP@10: 38.56
Rank counts only results with a code link.