{"id":"W4415987807","doi":"10.48550/arxiv.2508.21193","title":"Benchmarking Large Pretrained Multilingual Models on Québec French Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Pipeline (software); Benchmark (surveying); Variety (cybernetics); Language model; Word error rate","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007767501,0.0005528096,0.0005692718,0.0005196338,0.0002759652,0.0002373415,0.001430943,0.0005922866,0.0004803754],"category_scores_gemma":[0.0004526127,0.000571234,0.0003900982,0.0003993467,0.00005067833,0.000360478,0.001142886,0.001131148,0.000442269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002791324,"about_ca_system_score_gemma":0.0007871603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002413978,"about_ca_topic_score_gemma":0.002460325,"domain_scores_codex":[0.9963793,0.0002567746,0.0006741575,0.001485231,0.0005748775,0.0006296993],"domain_scores_gemma":[0.997283,0.0005211695,0.000337881,0.001312501,0.0003594667,0.0001859574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002851012,0.0006086987,0.007187373,0.0002403186,0.0002167945,0.0001406006,0.002033976,0.0002059525,0.000161644,0.00032427,0.002401199,0.9864507],"study_design_scores_gemma":[0.003357562,0.0004379502,0.04333394,0.005479074,0.0003265818,0.00006093875,0.0002783336,0.8235104,0.06939868,0.04023024,0.009251086,0.004335216],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8450714,0.0002193808,0.1101442,0.001205384,0.003108394,0.0009249897,0.0002560034,0.0009453677,0.03812485],"genre_scores_gemma":[0.9210513,0.0001494321,0.07358499,0.001828244,0.0006179876,0.00017772,0.0001953545,0.00003962713,0.002355351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9821154,"threshold_uncertainty_score":0.9996739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08065248834183726,"score_gpt":0.2909048515514014,"score_spread":0.2102523632095641,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}