Transkribus · Super Model · Published January 28, 2025

Faucon Français

Text RecognitionScholar+

Description

Faucon Français is a highly capable super model in Transkribus for recognising handwritten and printed French texts. Trained on an extensive French-language dataset enriched with community contributions, it is designed to handle a wide variety of documents, from medieval manuscripts to modern printed works. The model excels across different styles and periods of French writing, offering reliable performance for historical research, archival work, and contemporary projects alike.

Try this model

Faucon Français
Use this modelOpen in Transkribus
Low error rate6.6% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 6.6% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. Super Models are trained on very large and diverse datasets, making them robust across a wide range of handwriting styles and languages. Because of this diversity, a low CER on the validation set is a strong indicator of general-purpose quality.

Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.

Words2,345,518
Model ID274829
Languages
French