bosonai/AudioTokenBench download history
bosonai/AudioTokenBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 34 times (14 in the last 7 days), and 1,002 times in total. It ranks #354,957 among datasets by monthly downloads.
AudioTokenBench This is the evaluation dataset for HiggsTokenizer. It contains 3150 24khz audio samples across 4 subsets: Speech: 1,000 clips of 10 seconds audio, randomly sampled from DAPS. Music: 1,000 clips of 10 seconds audio, randomly sampled from MUSDB. Sound Event: 1,000 clips
Open bosonai/AudioTokenBench on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.