{"id":"W3119746889","doi":"10.48550/arxiv.2101.03027","title":"User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis","year":2020,"lang":"en","type":"preprint","venue":"SOAS Research Online (SOAS University of London)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; User Friendly; Front and back ends; Transcription (linguistics); Graphical user interface; Interface (matter); CUDA; User interface; Set (abstract data type); Speech recognition; Natural language processing; World Wide Web; Human–computer interaction; Programming language; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001245626,0.0003374579,0.0007896902,0.00113051,0.0002582079,0.0001059304,0.003308619,0.0003804218,0.0003858332],"category_scores_gemma":[0.0004694391,0.0003927691,0.0004528171,0.001135339,0.0005189083,0.0004104975,0.002296255,0.001427338,0.00008252778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002587598,"about_ca_system_score_gemma":0.000765352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001352977,"about_ca_topic_score_gemma":0.0006665481,"domain_scores_codex":[0.9953587,0.0009417914,0.0005099657,0.0009338866,0.001680504,0.0005751356],"domain_scores_gemma":[0.9967834,0.0005985752,0.0003698663,0.001164591,0.000719513,0.0003640565],"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":[0.0008184339,0.003546737,0.000774945,0.01769861,0.001652225,0.001845144,0.0428435,0.001018604,0.07238235,0.01190286,0.03244586,0.8130708],"study_design_scores_gemma":[0.01018117,0.002803241,0.008615137,0.01443898,0.0005737264,0.00008108121,0.05823267,0.6185158,0.1053181,0.01615184,0.1608433,0.004244864],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6177703,0.001164066,0.3499132,0.01970152,0.0003875821,0.002220336,0.0008550517,0.001032331,0.006955655],"genre_scores_gemma":[0.6859415,0.001239242,0.3098659,0.000166282,0.0002210178,0.000004266861,0.0005165199,0.00007217866,0.001973067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8088259,"threshold_uncertainty_score":0.9998524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04480315530894974,"score_gpt":0.3171667099757217,"score_spread":0.2723635546667719,"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."}}