How do I train a model?
Custom models are tailored to your specific documents, allowing you to achieve higher accuracy and more consistent results for unique or complex materials.
A Text Recognition model is an AI algorithm trained on a certain number of data (images and transcriptions), able to detect the most probable sequence of characters for each segmented text line.
- Upload your documents
- Recognise part of your document with a text recognition model
- Edit and correct the results of your recognition
- Train your own costum recognition models
- Recognise the rest of your material with your costum model
- Export and share your results
Depending on the type of material and the number of hands, between 5,000 and 15,000 words (around 25-75 pages) of transcribed material are required to start.
You can start the training of models by switching from the Home to the AI Lab view on the left sided navigation slide out. This is the dedicated AI training dashboard, where you can train not only Text Recognition models, but also Baselines, Field and Table models.
Your trained Text Recognition models are displayed under "My Models" by default when opening this page.
Under the section "Training" you can find all the models you trained and the co-relating training data. By clicking on "Train New Model" you can also start the training from here.
For more information on how and when to train your own text recognition model have a look at this article: Training Text Recognition Models.