David S. Batista

Hi @thirteenflt thanks a lot for making us aware of that, could you maybe open a PR to fix that? I would be really grateful.

I was getting similar errors when I had features that included `\n` characters or `\s`, try replacing those by a special token, e.g.: `#NEWLINE`, or `#SPACE`

can you past the command line you used?

I also would love to have this feature :)

Did you use Viterbi to do the decoding of the best sequence ? That might also explain the different results

wow, thanks - I even had forgotten about this :)

I've gathered a few [annotated datasets](https://www.notion.so/deepsetai/Proposal-for-presentation-of-RAG-Evaluation-Results-4b1063a227ad4e08950f184c014063da#baf448103469441cbc4d9863248f33e2 ) that could are fit for this.

Hi @Guest400123064, thanks for your contribution, this is very good work! I left some initial suggestions.