We’re always delighted to hear updates from Transkribus users about their progress!
Dr Richard Dunley from The National Archives in the UK has recently blogged about his team’s work on a model to process a collection of English Will registers.
The latest results are promising, with automated transcriptions reaching an average Character Error Rate of 14%. The National Archives enlisted the support of volunteers to produce further training data for their model and they are also looking forward to the possibility of exploiting the collection with the Keyword Spotting tool in Transkribus.
Read more at The National Archives blog.