Marian is a neural machine translation framework for training and running machine translation models. It provides tools for building neural networks that translate text between languages.
The framework is designed for computational efficiency, with an emphasis on performing training and translation operations directly using optimised numerical computation. It supports both recurrent neural network architectures and Transformer-based translation systems.
Marian is primarily intended for machine translation researchers and developers building translation services or experimenting with neural network architectures. Its command-line tools cover model training, validation and decoding, while its underlying implementation supports large-scale computational workloads.
This is free and open source software.
Key Features
- Training and inference for neural machine translation models.
- Support for Transformer and recurrent neural network architectures.
- Multi-GPU model training for computationally demanding translation workloads.
- CPU and GPU execution of trained translation models.
- Efficient batching of training examples and translation requests.
- Configurable neural network architectures and model hyperparameters.
- Attention mechanisms for sequence-to-sequence learning.
- Beam search decoding for generating translation hypotheses.
- Support for sequence-level training objectives.
- Configurable learning-rate scheduling and optimisation algorithms.
- Model checkpointing and training continuation.
- Validation during training using configurable evaluation metrics.
- Support for guided alignment and other translation training techniques.
- Model ensembling during translation.
- Command-line tools for training, translating and evaluating neural translation systems.
- Cross-platform support – runs on Linux, macOS, and Windows.
Website: github.com/marian-nmt/marian
Support:
Developer: Marian NMT contributors
License: MIT License
Marian is written in C++. Learn C++ with our recommended free books and free tutorials.
Related Software
| C++ Natural Language Processing Tools | |
|---|---|
| text2vec | Framework with API for text analysis and natural language processing |
| Moses | Statistical machine translation system |
| TiMBL | Tilburg Memory-Based Learner |
| MITIE | MIT Information Extraction |
| MeTA | Modern C++ data sciences toolkit |
| Colibri Core | Efficient n-gram & skipgram modelling on text corpora |
| CRF++ | Yet Another CRF toolkit |
| BLLIP Parser | Statistical natural language parser |
Read our verdict in the software roundup.
 LinuxLinks helps you discover the best free and open source software for Linux. Explore our extensive collection of recommended applications, including alternatives to popular proprietary software.We also publish software reviews, Linux tutorials, hardware reviews, free programming books and articles covering the wider open source community. Browse our Linux resources to discover more. Know a useful free and open source Linux application we haven't covered? Suggest a program for inclusion. Has your software been featured on LinuxLinks? Display one of our Featured on LinuxLinks badges on your website or GitHub README. |
Please read our Comment Policy before commenting.