Yasmin Moslem
@ymoslem.bsky.social
NLP Researcher at ADAPT Centre | PhD
Machine Translation, Speech, LLMs
Machine Translation, Speech, LLMs
Reposted by Yasmin Moslem
Yasmin Moslem, a researcher at the ADAPT Centre and @tcddublin.bsky.social, has had two papers accepted for presentation at the prestigious International Conference on Spoken Language Translation (#IWSLT) 2025. Learn more: www.adaptcentre.ie/news-and-eve...
August 1, 2025 at 10:28 AM
Yasmin Moslem, a researcher at the ADAPT Centre and @tcddublin.bsky.social, has had two papers accepted for presentation at the prestigious International Conference on Spoken Language Translation (#IWSLT) 2025. Learn more: www.adaptcentre.ie/news-and-eve...
Deployment of large audio-language models is challenging. In our #IWSLT2025 research, we compressed Qwen2-Audio-7B to be 50% smaller, while retaining #speech translation quality. We used a mix of ✂️ iterative layer pruning, 💿quantization, and 📚knowledge distillation. #NLProc
arxiv.org/abs/2505.20237
arxiv.org/abs/2505.20237
Efficient Speech Translation through Model Compression and Knowledge Distillation
Efficient deployment of large audio-language models for speech translation remains challenging due to their significant computational requirements. In this paper, we address this challenge through our...
arxiv.org
June 3, 2025 at 6:38 AM
Deployment of large audio-language models is challenging. In our #IWSLT2025 research, we compressed Qwen2-Audio-7B to be 50% smaller, while retaining #speech translation quality. We used a mix of ✂️ iterative layer pruning, 💿quantization, and 📚knowledge distillation. #NLProc
arxiv.org/abs/2505.20237
arxiv.org/abs/2505.20237