Good news! Looking forward to the many discoveries this work will surely reveal!
The first 500 pages of transcriptions are free, however, you may have to train the model on up to several hundred pages first.
"... Transkribus is the result of the READ project’s work to develop new technology to better recognise and automatically transcribe handwritten documents. These transcriptions can then help researchers better search for words or phrases among the billions of pages stored across the continent’s archives. ..."
"... Transkribus launched in 2015 as a collaboration between 17 archives, universities, and research groups across Europe. Some 45,000 users have trained 7,700 models so far.
Why it matters: Most optical character recognition approaches perform poorly on the millions of handwriting styles represented in historical archives. By transcribing and making these documents searchable and sortable, machine learning is helping to deepen our understanding of past people and events. ...
This platform could also be a gift to amateur historians with shoeboxes full of their forebears’ diaries, documents, and love letters."
This platform could also be a gift to amateur historians with shoeboxes full of their forebears’ diaries, documents, and love letters."
Credits to Andrew Ng's newsletter The Batch!
No comments:
Post a Comment