TranslateLocally: Blazing-fast translation running on the local CPU
This addresses privacy concerns for users and organizations requiring confidentiality, offering a practical alternative to online services.
The paper tackles the privacy and confidentiality issues of online machine translation by developing translateLocally, an open-source software that runs locally on CPUs, achieving cloud-like translation speed and quality on older hardware.
Every day, millions of people sacrifice their privacy and browsing habits in exchange for online machine translation. Companies and governments with confidentiality requirements often ban online translation or pay a premium to disable logging. To bring control back to the end user and demonstrate speed, we developed translateLocally. Running locally on a desktop or laptop CPU, translateLocally delivers cloud-like translation speed and quality even on 10 year old hardware. The open-source software is based on Marian and runs on Linux, Windows, and macOS.