| { |
| "schema": "etiquette combinee = indice_casse * 7 + indice_ponct, lue sur le premier sous-jeton de chaque mot normalise", |
| "cases": { |
| "L": "minuscule", |
| "C": "Capitale initiale", |
| "U": "TOUT EN MAJUSCULES", |
| "M": "mixte (forme lue dans tables.json['mixed'], sinon capitale apres la derniere apostrophe/trait d'union)" |
| }, |
| "puncts": [ |
| "O", |
| ",", |
| ".", |
| "?", |
| "!", |
| ":", |
| ";" |
| ], |
| "normalisation_entree": "evaluate_asr.normalize (minuscules, [a-z0-9'-], apostrophes/tirets unifies)", |
| "tables": "tables.json : 'mixed' = formes a casse mixte ; 'lex' = n-gramme normalise -> forme accentuee (ex. 'tan na' -> 'tanàna'), construite sur train + Wikipedia", |
| "base": "Davlan/xlm-roberta-base-finetuned-malagasy", |
| "entrainement": "work/punct/train.py --noise 0.5 --epochs 3 (checkpoint epoque 2.5)" |
| } |
