arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.03643cs.SDcs.AIeess.AS
收藏

语音基础模型的高效且有效的混合精度量化

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

The Chinese University of Hong Kong(香港中文大学);National Research Council Canada(加拿大国家研究委员会)

Haoning Xu, Zhaoqing Li, Zengrui Jin, Huimeng Wang, Youjun Chen, Guinan Li, Mengzhe Geng, Shujie Hu, Jiajun Deng, Xunying Liu

AI总结:

本研究提出一种将混合精度学习与参数量化整合至单阶段的语音基础模型混合精度量化新方法,在LibriSpeech数据集上验证了其在提升压缩比、缩短压缩时间的同时可维持甚至降低词错误率。

摘要:

本文提出了一种针对语音基础模型的新型混合精度量化方法,该方法将混合精度学习与量化模型参数估计紧密整合到单个模型压缩阶段中。在LibriSpeech数据集上,针对微调后的wav2vec2.0-base和HuBERT-large模型开展的实验表明,相较于采用分离且互不相交的阶段执行精度学习和模型参数量化的均匀精度基线与两阶段混合精度量化基线,所得混合精度量化模型的无损压缩比分别提升了最高1.7倍和1.9倍,同时相较于32位全精度模型,其词错误率(WER)未出现统计学意义上的升高。wav2vec2.0-base和HuBERT-large模型的系统压缩时间相较于两阶段混合精度基线分别减少了最高1.9倍和1.5倍,且两者的WER均更低。性能最佳的3.5位混合精度量化HuBERT-large模型相较于32位全精度系统实现了8.6倍的无损压缩比。

英文摘要:

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quantization in separate and disjointed stages, while incurring no statistically word error rate (WER) increase over the 32-bit full-precision models. The system compression time of wav2vec2.0-base and HuBERT-large models is reduced by up to 1.9 and 1.5 times over the two-stage mixed-precision baselines, while both produce lower WERs. The best-performing 3.5-bit mixed-precision quantized HuBERT-large model produces a lossless compression ratio of 8.6x over the 32-bit full-precision system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑