{"id":"W4200300291","doi":"10.21105/joss.03958","title":"Phonemizer: Text to Phones Transcription for Multiple Languages in Python","year":2021,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Python (programming language); Computer science; Transcription (linguistics); Programming language; World Wide Web; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063646,0.00009584673,0.0002349554,0.0001044546,0.0001120661,0.0002395507,0.001132866,0.00004090221,0.00009893067],"category_scores_gemma":[0.000755046,0.0000674933,0.0001107714,0.0003609129,0.00001562704,0.0004316275,0.0001515433,0.0001371733,0.00002875751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003909746,"about_ca_system_score_gemma":0.00009127984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005115387,"about_ca_topic_score_gemma":0.000142308,"domain_scores_codex":[0.9989563,0.000196368,0.000323042,0.0001302044,0.0002196102,0.0001744893],"domain_scores_gemma":[0.9986221,0.0006603096,0.0001468876,0.0002605898,0.0002255154,0.00008463876],"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":[0.0003523631,0.0002327349,0.001435178,0.00003322787,0.00005629579,0.00007144406,0.01624739,0.0005805076,0.03742747,0.00006368713,0.00960903,0.9338907],"study_design_scores_gemma":[0.01199955,0.0007724413,0.0282178,0.00138981,0.000172798,0.002465724,0.0312183,0.005129275,0.6591315,0.005547997,0.2526922,0.001262589],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1870693,0.0004824103,0.806583,0.005040823,0.0002754646,0.0003210375,0.000008833601,0.00003313802,0.000185949],"genre_scores_gemma":[0.6572593,0.00009387298,0.3381392,0.002467646,0.0001684445,0.0000210119,0.000002585846,0.00002806261,0.001819867],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9326281,"threshold_uncertainty_score":0.2752297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03478052608443864,"score_gpt":0.3024721744834523,"score_spread":0.2676916483990136,"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."}}