dialect-spot

Scores words for association with US, British, Australian and New Zealand English. Linear heads on a frozen mmBERT-small encoder.

Usage

import sys
from huggingface_hub import snapshot_download

path = snapshot_download("goldreal-ai/dialect-spot")
sys.path.insert(0, path)
from span_probes import load

probe = load(path)
probe.analyze("We parked the ute outside the servo")

Each word has character offsets, per-region probabilities and regions (regions above the calibrated threshold). Pass spans=[[(start, end), ...]] to score phrases instead of single words.

License

Heads: CC BY-SA 4.0. Encoder files: MIT (LICENSE-mmBERT).