headchem
commented
2 years ago Colab notebook for OCR and basic line break cleanup complete: https://colab.research.google.com/drive/1VhCx7kgj8j5Nraww6TFmJ1sdFXVszDuE?usp=sharing
Closed headchem closed 2 years ago
headchem
commented
2 years ago Colab notebook for OCR and basic line break cleanup complete: https://colab.research.google.com/drive/1VhCx7kgj8j5Nraww6TFmJ1sdFXVszDuE?usp=sharing
Add more full screenplays and all levels of summaries from very different genres. With the new admin-only reverse summarization models speeding up data entry, I can now focus my time on converting screenplays to the Fountain format, then complete all summary levels more quickly.
Maybe this ticket should be used to for a Colab notebook that does OCR on screenplay PDFs, removing page numbers, converting bold/italic to markdown, etc?