On-Device Speech Recognition With Whisper.cpp: Latency, Accuracy, and Memory
Whisper.cpp on a Raspberry Pi 5 achieves real-time transcription for short utterances. The latency budget at different model sizes and the memory footprint that limits deployment.
Whisper.cpp on a Raspberry Pi 5 achieves real-time transcription for short utterances. The latency budget at different model sizes and the memory footprint that limits deployment.
Overview
This note is part of the field-notes archive generated for this site. The summary below is the published excerpt; you can expand the full write-up anytime in the CMS.
Related notes
Tags
- speech-recognition
- whisper
- edge-ai
- raspberry-pi
- inference
Manish Bookreader
Electronics enthusiast, Embedded Systems Expert, Linux/Networking programmer, and Software Engineer passionate about AI, electronics, books, and cooking.