WIEWAVE home

Marian NMT on Azure

Fast C++ toolkit for training and serving neural machine translation models, compiled with CPU and GPU decoding support and example configurations. Built and maintained by WIEWAVE for Azure Marketplace, on Ubuntu and Debian.

Marian NMT at a glance

Key facts about Marian NMT
Built & maintained byWIEWAVE
CategoryAI & Machine Learning
Operating systemsUbuntu, Debian
MarketplacesAzure Marketplace
Offer typesPublic listing, with private offers on request

Availability by marketplace

Where Marian NMT is published
MarketplaceStatus
Azure MarketplacePublished
AWS MarketplaceAvailable on request
Google Cloud MarketplaceAvailable on request

Need it on another marketplace, or as a private offer for your organisation? cloud@wiewave.com

Operating systems

Marian NMT is built on 2 distributions

Each image follows its distribution's own provisioning model, package manager and security tooling — not one build relabelled several times.

  • Ubuntu

    LTS and interim releases, Minimal and Pro variants, built to Canonical's cloud-image conventions.

  • Debian

    Stable and oldstable, with backports where a workload needs a newer runtime than the release ships.

How it's built

How WIEWAVE builds and maintains this image

The same four steps behind every offer we've published, including the hardening and CIS Benchmark checks every build goes through.

  1. 01

    Scoped

    The distribution, licensing model and target marketplaces are agreed before anything is built.

  2. 02

    Built & hardened as code

    Packer templates, Ansible provisioning and a pinned package set — then hardened, scanned and checked against the CIS Benchmark for its distribution.

  3. 03

    Certified & published

    Taken through each cloud's own certification pipeline before it goes live on the marketplace.

  4. 04

    Maintained

    Rebuilt on the upstream security cadence and re-published, with old versions retired without breaking deployments.

FAQ

Marian NMT: common questions

If yours isn't here, ask our marketplace team directly.

AI & Machine Learning

More in AI & Machine Learning

GPU-ready training and inference images with drivers, CUDA and frameworks already matched to each other.

AI & Machine Learning

Mars-LM

Image providing a large language model runtime for text generation workloads, with GPU inference dependencies installed and a serving entry point.

Available on distributions:UbuntuDebian
Published onAzure Marketplace
AI & Machine Learning

Matplotlib

Python plotting library for static charts and figures, installed with NumPy and headless rendering backends so images can be generated server-side.

Available on distributions:UbuntuDebianRHELAlmaLinuxRocky
Published onAzure Marketplace, AWS Marketplace, Google Cloud Marketplace
AI & Machine Learning

MazeRL

Applied reinforcement learning framework for building and training agents, offering configurable environments, distributed rollouts and PyTorch-based policy implementations.

Available on distributions:UbuntuDebian
Published onAzure Marketplace
AI & Machine Learning

MediaPipe

Google's cross-platform perception framework, shipped with Python bindings and pretrained pipelines for face, hand, pose and object detection on images or video.

Available on distributions:UbuntuDebian
Published onAzure Marketplace, AWS Marketplace, Google Cloud Marketplace
AI & Machine Learning

Meetrix Transcriber with API

Speech-to-text transcription service from Meetrix that accepts audio uploads over a REST API and returns written transcripts of meetings and recordings.

Available on distributions:Ubuntu
Published onAzure Marketplace
AI & Machine Learning

MegEngine

Deep learning framework from Megvii with unified training and inference paths, installed as a Python package with CPU and GPU execution support.

Available on distributions:UbuntuDebian
Published onAzure Marketplace
See all 247 products in AI & Machine Learning

Need Marian NMT customised, or on another cloud?

Tell us the distribution, the marketplace and the commercial model — we'll build, certify and publish it as a public listing or a private offer.