HKUSTAudio/AudioX-IFcaps download history
HKUSTAudio/AudioX-IFcaps is a text to audio dataset on the Hugging Face Hub. In the last 30 days it was downloaded 18 times (6 in the last 7 days), and 602 times in total. It ranks #402,156 among datasets by monthly downloads.
[ICLR 2026] AudioX-IFcaps: Instruction-Following Audio Caption Dataset AudioX-IFcaps (Instruction-Following) is a large-scale, high-quality multimodal dataset designed for training unified audio and music generation models. The dataset contains over 7 million samples with fine-grained,