Pipeline output no longer matches the provided example
Hi,
I used your model to modernize text, and everything was fine, but over the past few weeks, I have been encountering issues with the outputs. Even the provided examples no longer match the expected results. As shown below, in the first sentence, we have 'haissoit' instead of 'haissait'. In the second one, the accent is missing on 'grace'. The third sentence is even stranger, with parts of words being repeated and 'Fr' appearing instead of 'à'
list_inputs = ["Elle haïſſoit particulierement le Cardinal de Lorraine;", "Adieu, i'iray chez vous tantoſt vous rendre grace.","Le Loup ne fut pas longtems à arriver à la maiſon de la Mere-grand, il heurte: Toc, toc, qui eſt là?"]
output :
['Elle haïssoit particulièrement le Cardinal de Lorraine;',"Adieu, j'irai chez vous tantôt vous rendre grace.", 'Le Loup ne fut pas longtems à arriver Fr la maison ne fut Pas-grand, est heurte ne Toc, long, qui est là?']
Thank you very much for your help !