{"id":674,"slug":"williamsanderson--medqa-darija-multilingual","name":"MedQA-Darija-MultiLingual","author":"Williamsanderson","description":"\n\t\n\t\t\n\t\tMedQA-Darija-MultiLingual\n\t\n\nThe largest open trilingual medical Q&A dataset with directly-playable speech audio for English, French, and Moroccan Darija.\nA research dataset for the BRAIN HEALTH initiative, designed for multilingual medical NLP, low-resource speech recognition, healthcare chatbots, and clinical education tools targeting Morocco and the broader Maghreb region.\n\nDataset is currently in scientific validation phase. After programmatic validation (Stage 1 LOF outlier… See the full description on the dataset page: https://huggingface.co/datasets/Williamsanderson/MedQA-Darija-MultiLingual.","tags":"[\"Task_categories:question-Answering\",\"Task_categories:automatic-Speech-Recognition\",\"Task_categories:text-To-Speech\",\"Language:ar\",\"Language:fr\",\"Language:en\"]","license":null,"framework":null,"parameters":null,"downloads":112258,"likes":4,"verified":0,"created_at":"2026-06-29 11:23:27","updated_at":"2026-06-29 15:23:28","source_url":"https://huggingface.co/datasets/Williamsanderson/MedQA-Darija-MultiLingual","source_platform":"huggingface","hf_repo_id":"Williamsanderson/MedQA-Darija-MultiLingual","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":673,"model_id":674,"version":"v1.0.0","manifest_hash":"7c80375628582b5a3360b4d927803019686765d31036a4c4c3c8d918e8579a8f","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/williamsanderson--medqa-darija-multilingual/v1.0.0.json","created_at":"2026-06-29 11:23:27"}],"files":[],"signatures":[{"id":1231,"version_id":673,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"5713968574c9aa52894b5b66b9a4a0c5ee96a1f12067602459d94d12441ef3d5","attestation_type":"registry","signed_at":"2026-06-29 11:23:27"}],"hndl":null}