
Overview This handwriting recognition model has been fine-tuned using the HTR model for German manuscripts trained from several datasets as base model in eScriptoirum. The ground-truth dataset for the transcriptions is available here. The model fine-tunes a generic model for german handwriting for the recognition of a single hand (that of Fanny Mendelssohn) and a particularly difficult medium (letters and notes written without much attention to form and sometimes slightly damaged). It achieves significantly better results on test-pages than the base model. Future Work Currently, this model works well on test data from the dataset of letters and notes by Fanny Mendelssohn to Wilhelm Hensel. In order to train a model that works well on Fanny Mendelssohn's hand more generally, more and diverse samples of her handwriting should be added to the training set.
automatic-text-recognition
automatic-text-recognition
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
