{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003444198,0.00574999,0.001492788,0.002153551,0.002045101,0.002594821,0.003724955,0.002284487,0.01023155],"category_scores_gemma":[0.009263452,0.0008470995,0.00157712,0.002048162,0.001113595,0.002075325,0.002422854,0.003159025,0.008385903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008143876,"about_ca_system_score_gemma":0.006735001,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6490577,"about_ca_topic_score_gemma":0.6875228,"domain_scores_codex":[0.9968172,0.0008483496,0.0001668371,0.001227876,0.0005077063,0.0004320146],"domain_scores_gemma":[0.9951788,0.001733425,0.00009600248,0.0007349897,0.002004422,0.0002523445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001692171,0.0009621583,0.01274275,0.001134561,0.001784665,0.0009883194,0.0007167754,0.357443,0.01673328,0.002346391,0.160744,0.4427119],"study_design_scores_gemma":[0.0002641037,0.0003790623,0.01211606,0.000176924,0.0003807597,0.0003085528,0.0008005888,0.939531,0.01781233,0.001584325,0.02647465,0.0001716166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6425737,0.01595306,0.1455278,0.003162495,0.003056544,0.001367241,0.06398875,0.08550067,0.03886985],"genre_scores_gemma":[0.692205,0.001926143,0.08106428,0.001299551,0.0003130937,0.0009323952,0.1918723,0.002879721,0.02750754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3509423,"threshold_uncertainty_score":0.706018,"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."}}