This repository will be used to release machine learning models for the use of tika-dl module of Apache Tika toolkit. In particular, the models could be pre-trained weights and metadata files of Tensorflow, Keras or DL4J.
If you use this work, please cite USC Data Science.
Send them to Chris A. Mattmann or Thejan Wijesinghe
Pull requests are welcome. If you like to add a deep learning based parser to Apache Tika or fix a bug or improve a current parser, please open an issue first in Tika Issue Tracker to discuss what you would like to add or change.
- Chris A. Mattmann, JPL & USC
- Thejan Wijesinghe, University of Moratuwa