Skip to content
#

reportlab-python

Here are 10 public repositories matching this topic...

A research prototype that classifies suicide risk from text and speech audio in English and Hindi. It combines a fine-tuned XLM-RoBERTa text encoder with a frozen OpenAI Whisper audio encoder through a learned gated fusion layer, trained with a multi-task objective and evaluated with 5-fold stratified cross-validation.

  • Updated Oct 1, 2026
  • Jupyter Notebook

Add this topic to your repo

To associate your repository with the reportlab-python topic, visit your repo's landing page and select "manage topics."

Learn more