TTS-AGI/levo2-vocals-captioned download history

TTS-AGI/levo2-vocals-captioned is an audio classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 526 times (17 in the last 7 days), and 1,964 times in total. It ranks #31,866 among datasets by monthly downloads.

LeVo 2 Vocals — 8,582 captioned a cappella singing clips 8,582 synthetic solo-singing / a cappella clips generated with LeVo 2 (gen_type: vocal), each with a detailed prose caption written by Gemini 3 Flash from the audio itself, plus structured vocal-texture flags, a music-aesthetics

Models trained on levo2-vocals-captioned

2 models list it as training data.

Open TTS-AGI/levo2-vocals-captioned on Hugging Face

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