{"_id":"6a3007ce5c4b5ce7123111a3","id":"MatBar99/HALAS","author":"MatBar99","sha":"317cef3a10d1097edc37e8eb1c007f415e3d0c55","lastModified":"2026-06-18T15:24:57.000Z","private":false,"gated":false,"disabled":false,"tags":["task_categories:automatic-speech-recognition","task_categories:audio-classification","task_categories:text-classification","annotations_creators:expert-generated","multilinguality:monolingual","source_datasets:earnings22","language:en","license:unknown","size_categories:1K<n<10K","format:csv","modality:text","modality:audio","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","asr","speech-recognition","speech-processing","hallucination","hallucination-detection","whisper","earnings22","benchmark","human-annotations","error-detection","audio","speech-to-text","robustness"],"description":"\n\t\n\t\t\n\t\n\t\n\t\tDataset Card for HALAS\n\t\n\n\n\t\n\t\t\n\t\n\t\n\t\tDataset Summary\n\t\n\nHALAS (Hallucination Annotations for Large-scale ASR Systems) is a human-annotated dataset of hallucinations produced by modern automatic speech recognition (ASR) systems on real-world speech recordings. The dataset contains span-level hallucination annotations for ASR outputs generated from recordings in the Earnings22 corpus.\nHALAS was introduced to address a key limitation in prior hallucination research: most existing… See the full description on the dataset page: https://huggingface.co/datasets/MatBar99/HALAS.","downloads":80,"likes":0,"cardData":{"language":["en"],"license":"unknown","task_categories":["automatic-speech-recognition","audio-classification","text-classification"],"annotations_creators":["expert-generated"],"source_datasets":["earnings22"],"multilinguality":["monolingual"],"size_categories":["1K<n<10K"],"pretty_name":"HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems","tags":["asr","speech-recognition","speech-processing","hallucination","hallucination-detection","whisper","earnings22","benchmark","human-annotations","error-detection","audio","speech-to-text","robustness"],"dataset_info":[{"config_name":"default","features":null},{"name":"audio_id","dtype":"string"},{"name":"audio_duration","dtype":"float32"},{"name":"e22_reference_text","dtype":"string"},{"name":"corrected_reference_text","dtype":"string"},{"name":"whisper_large_v2_prediction","dtype":"string"},{"name":"whisper_large_v2_label","dtype":"bool"},{"name":"whisper_large_v2_hallucination_text","dtype":"string"},{"name":"whisper_large_v2_hallucination_json","dtype":"string"},{"name":"whisper_large_v3_prediction","dtype":"string"},{"name":"whisper_large_v3_label","dtype":"bool"},{"name":"whisper_large_v3_hallucination_text","dtype":"string"},{"name":"whisper_large_v3_hallucination_json","dtype":"string"},{"name":"whisper_large_v3_turbo_prediction","dtype":"string"},{"name":"whisper_large_v3_turbo_label","dtype":"bool"},{"name":"whisper_large_v3_turbo_hallucination_text","dtype":"string"},{"name":"whisper_large_v3_turbo_hallucination_json","dtype":"string"},{"name":"crisper_whisper_prediction","dtype":"string"},{"name":"crisper_whisper_label","dtype":"bool"},{"name":"crisper_whisper_hallucination_text","dtype":"string"},{"name":"crisper_whisper_hallucination_json","dtype":"string"},{"name":"canary_prediction","dtype":"string"},{"name":"canary_label","dtype":"bool"},{"name":"canary_hallucination_text","dtype":"string"},{"name":"canary_hallucination_json","dtype":"string"},{"name":"canary_flash_prediction","dtype":"string"},{"name":"canary_flash_label","dtype":"bool"},{"name":"canary_flash_hallucination_text","dtype":"string"},{"name":"canary_flash_hallucination_json","dtype":"string"},{"name":"parakeet_prediction","dtype":"string"},{"name":"parakeet_label","dtype":"bool"},{"name":"parakeet_hallucination_text","dtype":"string"},{"name":"parakeet_hallucination_json","dtype":"string"},{"name":"phi4_prediction","dtype":"string"},{"name":"phi4_label","dtype":"bool"},{"name":"phi4_hallucination_text","dtype":"string"},{"name":"phi4_hallucination_json","dtype":"string"},{"name":"granite_prediction","dtype":"string"},{"name":"granite_label","dtype":"bool"},{"name":"granite_hallucination_text","dtype":"string"},{"name":"granite_hallucination_json","dtype":"string"},{"name":"split","dtype":"string","splits":[{"name":"train","num_examples":2866},{"name":"test","num_examples":745}]}],"configs":[{"config_name":"default","data_files":[{"split":"train","path":"train.csv"},{"split":"test","path":"test.csv"}]}],"paperswithcode_id":null,"train_eval_index":[{"config":"default","task":"hallucination-detection","split":"test"}]},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"HALAS_dataset.csv"},{"rfilename":"README.md"},{"rfilename":"prompt.txt"},{"rfilename":"test.csv"},{"rfilename":"train.csv"}],"createdAt":"2026-06-15T14:10:22.000Z","usedStorage":1236209}