SpeechAntiSpoofingBenchmarks/SONAR download history

SpeechAntiSpoofingBenchmarks/SONAR is an audio classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,208 times (226 in the last 7 days), and 6,210 times in total. It ranks #16,765 among datasets by monthly downloads.

SONAR Benchmark-ready packaging of the SONAR synthetic-audio detection evaluation set (arXiv 2410.04324), for speech anti-spoofing and synthetic / deepfake voice detection. Overview SONAR is a binary-classification benchmark: bonafide (genuine human speech) vs. spoof (A

Open SpeechAntiSpoofingBenchmarks/SONAR on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.