20th Century Typewritten Italian

This model was created by the Historical Archive of Mediobanca, an Italian investment bank, to transcribe a variety of typewritten documents in Italian and English, such as correspondence, articles, meetings' minutes, memos. The training set consists of 28.137 words. The model is trained to expand abbreviations specific to banking activities and people’s honorifics. Mediobanca's internationalization has left many documents in English, so "Transkribus Print M1" was used as the base model: even if "20th Century Typewritten Italian" is specifically geared towards the Italian language, the model was also tested on documents in English, proving to be able to recognize words and short sentences with satisfying results. This model achieved a Character Error Rate of 0.82%. This model was created alongside the "20th Century Typewritten Letters - Diplomatics' Elements" Field Model, as part of a larger project. It was trained by Silvia Carboni for Mediobanca's Historical Archive.