00:00
2026-06-30
aclanthology.org
large-language-models
HW-TSC’s Submission to the IWSLT 2026 Subtitling Track
HW-TSC submitted a cascaded system to the IWSLT 2026 Subtitling track, using a large-model-based streaming speech recognition framework with VAD, sliding-window context caching, long audio chunking, a…