datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
text_interference_vocalsoundaudio_interference_mmluLCAR-Hallucination-Benchmark
LCAR Hallucination Benchmark
LCAR Hallucination Benchmark is a manually reviewed speech benchmark for
studying acoustic-grounding failures in LLM-based ASR. It contains two
500-utterance suites: controlled speech synthesized with IndexTTS2 and speech
derived from openly released corpora. The benchmark covers translation or
transliteration, spoken or text-prompt instruction execution, unsupported
repetition, and catastrophic deletion.
The benchmark is a targeted stress set. It is… See the full description on the dataset page: https://huggingface.co/datasets/aguangguang/LCAR-Hallucination-Benchmark.text_interference_urbansound8kINSPIRE
INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval
Overview
INSPIRE is a benchmark for evaluating instruction-aware speech retrieval systems with open-ended instructions. It provides tools for building and evaluating speech retrieval models that can handle diverse retrieval tasks specified through natural language instructions. The benchmark includes dataset processing, feature extraction, and evaluation metrics.
Motivation
Traditional… See the full description on the dataset page: https://huggingface.co/datasets/lca0503/INSPIRE.audio_interference_gsm8ktext_interference_mmauinterleaving_mmau_fastest_tempospeech_mmau_fastest_tempospeech_mmau_slowest_tempofaster_speech_mmauaudio_interference_arc_challengespeech_mmau_highest_pitchinterleaving_mmau_slowest_tempointerleaving_mmau_lowest_pitchfaster_interleaving_mmauinterleaving_mmau_highest_pitchspeech_mmau_lowest_pitchINSPIRE-voxceleb1lcaudiodataseticaro2ICAROIAVicaroia