Janneke van der Zwaan

Actually, I started doing this, see ecf755d3b3fdadad72c9b6288da5b1a40b37b40f However, for searching it is not so easy, because the cli allows you to specify whether you want to do a fuzzy search...

> I am wondering how to specify CC='gcc-8' CXX='g++-8' when installing pytrec_eval. `$ CC='gcc-8' CXX='g++-8' pip install pytrec_eval`

Thank you for your interest in ochre. As mentioned in the README, it is not a product that can be used as is. I'm sorry but we do not have...

1. Thank you for your remark, I added some documentation 2. There is no need to regenerate this workflow, and I also see that the notebook is outdated. Newer version...

Sorry for my late reply, I also have been busy with other projects. I think ochre could be useful for you. It uses an existing tool to calculate wer and...

So, I have updated the documentation and added the workflows for calculating performance. You don't need a lot of Python knowledge, just follow the installation instructions and adjust the paths...

I had similar results (although I only trained for a single iteration, it was clear performance was not as good as for the other data I tried). My first guess...

The task ochre performs is a supervised machine learning task. So, without gold standard, you can't create aligned data or train a (supervised) model.

The README specifies how to use a trained model to do post correction: https://github.com/KBNLresearch/ochre#ocr-post-correction If you want to calculate performance for this text, you'd still need to have ground truth/gold...

No, I'm afraid there are no pretrained models available.