Sign language subtitle alignment on WMT-SLT (test)
77.69F1@0.50SignCLIP-BSL/ASL/DSGS-finetuned
Evaluation results
| Method | Links | |
|---|---|---|
| SignCLIP-BSL/ASL/DSGS-finetunedAlignment Approach=Segment, Embed, and Align, Strategy=finetuned2025.12 | 77.69 | |
| SegmentationAlignment Approach=Segment and Align2025.12 | 76.83 | |
| SignCLIP-multilingualAlignment Approach=Segment, Embed, and Align, Strategy=multilingual2025.12 | 76.43 | |
| SATModel Type=End-to-end trained2025.12 | 75.32 | |
| Original+ (fixed offsets from training data)Alignment Approach=Fixed offsets2025.12 | 74.83 | |
| Original alignment (usually audio-based)Alignment Approach=Audio-based2025.12 | 46.85 |