nvidia/AudioSkills download history

nvidia/AudioSkills is an audio text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,250 times (361 in the last 7 days), and 38,757 times in total. It ranks #16,414 among datasets by monthly downloads.

AudioSkills-XL Dataset Project page | Paper | Code Dataset Description AudioSkills-XL is a large-scale audio question-answering (AQA) dataset designed to develop (large) audio-language models on expert-level reasoning and problem-solving tasks over short audio clips (≤30 second

Models trained on AudioSkills

7 models list it as training data.

• nvidia/audio-flamingo-3-hf 52.4K downloads in 30 days
• nvidia/audio-flamingo-3 3.4K downloads in 30 days
• nvidia/audio-flamingo-3-chat 207 downloads in 30 days
• Visionboxx/audio-flamingo-3 16 downloads in 30 days
• nvidia/audio-flamingo-2-SoundCoT 0 downloads in 30 days
• nvidia/audio-flamingo-2 0 downloads in 30 days
• salvatore2303/audio – downloads in 30 days

Open nvidia/AudioSkills on Hugging Face

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