Skip to content
SPECIFICTION
Get listed

EasyNMT

github.com

LinuxAPISelf-hosted
Visit github.com
Spec score 7.5 #109 of 156 in Translation Software

Spec sheet

Product
EasyNMT is a Python package for neural machine translation across more than 100 languages.Read 13 Oct 2026 · github.com
Integrations
The README describes PyTorch-based models, fastText language detection, Docker images, and a Google Colab hosting example.Read 12 Oct 2026 · github.com
Support
The author invites users to email or report an issue if something is broken or they have questions.Read 13 Oct 2026 · github.com
License
The repository lists the Apache-2.0 license.Read 13 Oct 2026 · github.com
API access
YesRead 22 Sep 2026 · github.com
API endpoints
The Docker documentation lists translation, language detection, and supported-language endpoints.Read 13 Oct 2026 · github.com
Document limit
The README states input limits of 512 word pieces for Opus-MT and 1024 for M2M models, with automatic sentence splitting for longer documents.Read 13 Oct 2026 · github.com
Document translation
YesRead 22 Sep 2026 · github.com
Installation
The README gives `pip install -U easynmt` as the installation command.Read 13 Oct 2026 · github.com
Intended audience
The repository describes the software as experimental and intended to encourage future research.Read 13 Oct 2026 · github.com
Language coverage
The README says Opus-MT supports 1200+ translation directions across 150+ languages.Read 13 Oct 2026 · github.com
Language detection
It can automatically detect source languages using fastText, with the README citing support for more than 170 languages.Read 12 Oct 2026 · github.com
License and security
The repository is published under the Apache-2.0 license; the opened project pages do not state security certifications or compliance claims.Read 12 Oct 2026 · github.com
Local models
The Docker documentation says model files are stored at `/cache/`, which can be mounted on the host for reuse.Read 13 Oct 2026 · github.com
Model availability
The README says the 12-billion-parameter M2M model is not supported and lists M2M-100 models with 418 million and 1.2 billion parameters.Read 12 Oct 2026 · github.com
Model limits
The README states input limits of 512 word pieces for Opus-MT and 1,024 for M2M models; longer documents are split into sentences for translation.Read 12 Oct 2026 · github.com
Models
Available model wrappers include Opus-MT, mBART50, and M2M_100.Read 13 Oct 2026 · github.com
Parallel processing
EasyNMT lists multi-GPU and multi-process translation as features.Read 13 Oct 2026 · github.com
Release
PyPI lists EasyNMT version 2.0.2, released May 27, 2022.Read 12 Oct 2026 · pypi.org
REST API
The project provides Docker images that expose EasyNMT as a REST API.Read 13 Oct 2026 · github.com
Translation
The project README describes sentence and document translation and automatic language detection for 170+ languages.Read 13 Oct 2026 · github.com

Where Specifiction places it

Alternatives to EasyNMTAll alternatives →