Peer-reviewed research
Performance and Efficiency Evaluation of ASR Inference on the Edge
Santosh Gondi and Vineel Pratap, Sustainability (MDPI), 2021
Read the originalRead on October 17, 2026
- What it is
- A 2021 study of speech recognition inference on edge hardware. The authors measured energy with an off-the-shelf USB meter on a Raspberry Pi and tested how accuracy and energy trade off, with and without quantization.
- How much weight it carries
- Peer-reviewed. The hardware is a single-board computer rather than a laptop or phone, the models are transformer ASR models of their time, and the study is short. Use it for the shape of the trade-off, not for battery figures.