NURC-SP

SAMPA: Whisper-based prosodic boundary segmentation for Brazilian Portuguese

Researchers introduce SAMPA, a Whisper large-v3 fine-tuned model for automatic prosodic boundary segmentation in Brazilian Portuguese speech. The model is trained on the NURC-SP dataset and achieves F1=0.731 on held-out test data and F1=0.796 on the out-of-distribution MuPe-Diversidades dataset. The work addresses a gap in NLP tooling for Brazilian Portuguese, where prior approaches relied on rule-based or traditional ML methods rather than modern deep learning.