Talmud Punctuator Model A-Q

BEREL 3.0 fine-tuned exclusively on Al HaTorah Berakhot. It predicts ordinary punctuation plus opening and closing quotation boundaries with separate heads. The ASCII sequences ?! and !? are one merged semantic interrobang class, rendered canonically as ?!.

  • Best held-out epoch: 6
  • Punctuation accuracy: 0.9558
  • Opening-quote F1: 0.9169
  • Closing-quote F1: 0.9040
  • Interrobang F1: 0.2667
  • Training source: Al HaTorah only

This is an experimental held-out model. Straight source quotes were interpreted at token edges after expanding Al HaTorah abbreviation markup; output quotes are directional curly quotes. The current supervision includes all source quotation spans, not only spans independently verified as biblical quotations.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Joshua2/talmud-punctuator-A-quotes

Finetuned
(8)
this model