datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
humans-benchmark
HUMANS Benchmark Dataset
Authors: Woody Haosheng Gan¹, William Held²'³, Diyi Yang²
¹University of Southern California, ²Stanford University, ³OpenAthena
This dataset is part of the Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment paper.
HUMANS (HUman-aligned Minimal Audio evaluatioN Subsets for Large Audio Models) Benchmark is designed to efficiently evaluate Large Audio Models using minimal subsets while predicting human preferences through learned… See the full description on the dataset page: https://huggingface.co/datasets/woodygan/humans-benchmark.humans-benchmark
HUMANS Benchmark Dataset (Anonymous, Under Review)
This dataset is part of the HUMANS (HUman-aligned Minimal Audio evaluatioN Subsets for Large Audio Models) Benchmark, designed to efficiently evaluate Large Audio Models using minimal subsets while predicting human preferences through learned regression weights.
Installation
Install the HUMANS evaluation package from GitHub (our anonymous repo):
# Option 1: Install via pip
pip install… See the full description on the dataset page: https://huggingface.co/datasets/HUMANSBenchmark/humans-benchmark.