How a hackathon dictation app running Speechmatics on-device speech-to-text exposed why real-time diarization needs GPU acceleration, CoreML, and DirectML.
Source: [HackerNoon](https://hackernoon.com/cloud-or-local-speech-to-text-we-built-the-same-app-both-ways-heres-what-we-learnt?source=rss)