<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e1196" altimg="si14.svg"> <mml:mrow> <mml:mi mathvariant="script">H</mml:mi> <mml:mi mathvariant="italic">andscribe</mml:mi> </mml:mrow> </mml:math> : A gloss-free framew

Sign language translation systems traditionally rely on intermediate gloss representations to bridge the gap between visual input and written language output. However, manual gloss annotation is costly, language-dependent, and often lossy, prompting growing interest in gloss-free alternatives. This paper introduces H andscribe , a novel two-stage framework for gloss-free sign language translation and gloss sequence generation. H andscribe first translates continuous sign language videos into written language sentences using a lightweight decoder built atop SlowFast-based spatiotemporal features and a frozen mBART model. Then, in the second stage, it generates gloss sequences from these sentences using a Large Language Model (LLaMa3.1-8B-Instruct) that has been fine-tuned with weak supervision. Our experiments on PHOENIX-2014-T and Wav2Gloss Fieldwork demonstrate strong translation performance and state-of-the-art multilingual gloss generation, even in zero-shot settings. The proposed framework reduces annotation bottlenecks while maintaining flexibility and interpretability, paving the way for scalable and inclusive sign language technologies. The code and fine-tuning scripts are available at https://github.com/colonnaemanuele/Handscribe . • We propose a gloss-free framework for sign language translation and gloss sequence generation. • Our method leverages SlowFast features and a frozen mBART decoder. • Glosses are inferred post-translation using a fine-tuned Large Language Model. • The approach eliminates the need for gloss-level supervision during training. • We report strong results on PHOENIX-2014-T and Wav2Gloss benchmarks.