2-bit Conformer quantization for automatic speech recognition

Understand

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.