# NMT Marian Framework Demo

NMT Marian Framework Demo is a self-hosted demonstration of the Marian neural machine translation (NMT) framework that runs on your own hardware, translating text between languages without external services. It is open source and self-hosted, installable on Docker Hub.

Canonical page: https://ourlocalhost.com/app/5863/nmt-marian-framework-demo

## Description

NMT Marian Framework Demo is a self-hosted demonstration of the Marian neural machine translation (NMT) framework that runs on your own hardware, translating text between languages without external services. It is ideal for organizations needing secure, high-quality translations while keeping their data completely confidential.

## Platform availability

Available on 0 of 10 platforms.

## Health score

32/100 (Low), based on 4 of 5 factors.
- Maintained: 0 (last commit 1369 days ago)
- Popular: 63 (1,476 GitHub stars)
- Easy to install: 25 (0 install platforms, install notes, Docker image)
- Security check: 65 (no serious findings, 1 minor, CI, tests, OpenSSF Scorecard 3/10)

## Links

- Docker Hub: https://hub.docker.com/r/intel/nmt_marian_framework_demo
- Official website: https://marian-nmt.github.io
- GitHub: https://github.com/marian-nmt/marian

## Common questions

### How should Marian config files be formatted?

Marian config files use INI format, where lines starting with ; are comments and square-bracket sections such as [default] group settings. Put each option in the correct section, or the app may ignore it and run with defaults.

### How can I set common model architecture and training options?

Marian provides --task options as a shortcut for setting model architecture and training options for common NMT model configurations. The documentation lists the predefined configurations.

### How do I compile Marian with a custom feature set?

The Marian build system uses CMake to compile the framework with various configurations. It supports cross-platform builds and fine-grained control over features and optimizations.

### What guidance is available for using custom Marian models with Hugging Face Transformers?

A Hugging Face discussion asks how to use custom Marian-NMT models, including models from the Opus-MT repository, with Transformers.

---
Source: Our Local Host (https://ourlocalhost.com/app/5863/nmt-marian-framework-demo), the self-hosted and open-source app directory.
