BaldWhisper model achieves 48% size reduction and 2.15x speedup

Researchers have developed BaldWhisper, a method to significantly compress and accelerate the Whisper speech-to-text model. By employing low-rank decomposition for embeddings and merging transformer layers, BaldWhisper achieves a 48% reduction in model size and a 2.15x speed increase on a MacBook Air M1. This approach maintains 90% of the original performance, even in data-scarce scenarios like the Bambara language with only 32 hours of training data. AI

影响 Offers a path to deploy powerful speech-to-text models on edge devices with limited data.

排序理由 This is a research paper detailing a new method for model compression and acceleration. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

• BaldWhisper
• Bambara
• MacBook Air M1
• Whisper
• Yaya Sy

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →