用于自动语音识别的2-bit Conformer量化
2-bit Conformer quantization for automatic speech recognition
AI总结：
本文研究将ASR模型权重量化至2-bit，结合对称/非对称量化、子通道量化和裁剪，在LibriSpeech上实现无损且模型缩小32%，在大规模数据上缩小超40%但词错误率相对上升17%。
摘要：
大型语音模型正在研究界迅速获得关注。因此，模型压缩已成为一个重要课题，以便这些模型能够装入内存并以更低的成本提供服务。压缩自动语音识别（ASR）模型的实用方法使用int8或int4权重量化。在本研究中，我们提出开发2-bit ASR模型。我们探索了对称和非对称量化结合子通道量化和裁剪在LibriSpeech数据集和大规模训练数据上的影响。我们在LibriSpeech上获得了一个无损的2-bit Conformer模型，与最先进的4-bit Conformer模型相比，模型大小减少了32%。在大规模训练数据上，我们获得了一个2-bit Conformer模型，与4-bit版本相比，模型大小减少了40%以上，代价是词错误率相对下降17%。
英文摘要：
Large speech models are rapidly gaining traction in research community. As a result, model compression has become an important topic, so that these models can fit in memory and be served with reduced cost. Practical approaches for compressing automatic speech recognition (ASR) model use int8 or int4 weight quantization. In this study, we propose to develop 2-bit ASR models. We explore the impact of symmetric and asymmetric quantization combined with sub-channel quantization and clipping on both LibriSpeech dataset and large-scale training data. We obtain a lossless 2-bit Conformer model with 32% model size reduction when compared to state of the art 4-bit Conformer model for LibriSpeech. With the large-scale training data, we obtain a 2-bit Conformer model with over 40% model size reduction against the 4-bit version at the cost of 17% relative word error rate degradation
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。
