# UKPLab/EasyNMT

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

Repository: https://github.com/UKPLab/EasyNMT
Canonical: https://ross.abutalabs.com/products/easynmt
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-12-21T15:05:23+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2052, "days_push": 986, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1260, forks 123 (observed 2026-08-28T04:04:09.906032+00:00)

## What it is
EasyNMT is a Python library providing easy access to state-of-the-art neural machine translation for 100+ languages using models like Opus-MT, mBART50, and M2M_100. It supports automatic language detection, sentence and document translation, multi-GPU/multi-process translation, and ships with Docker images exposing a REST API.

## Use cases
- translate text between 100+ languages in python
- detect the language of a sentence automatically
- batch translate documents with a pretrained model
- host a machine translation REST API in docker
- run translation on multiple GPUs
- translate a mixed-language list of sentences to one target language

## When to choose
- you need simple, few-lines-of-code neural translation in Python
- you want automatic model download and language detection
- you need a ready-made Dockerized translation REST API
- you want multi-GPU or multi-process translation throughput

## When to avoid
- you need fine-grained control over model training or custom translation models
- you need the newest models or active updates (last release was late 2023)
- you need translation for very low-resource languages not covered by Opus-MT, mBART, or M2M_100

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, llm-inference
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: neural-machine-translation, translation, opus-mt, mbart, m2m100, rest-api, language-detection, natural-language-processing, docker, gpu

## Member repositories
- UKPLab/EasyNMT (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.906032+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:22.297315+00:00, confidence not recorded.
  - readme: https://github.com/UKPLab/EasyNMT (fetched 2026-08-28T04:04:09.906032+00:00, sha c4c8fc110e67)
  - registry_pypi: https://pypi.org/pypi/easynmt/json (fetched 2026-08-29T12:17:01.981669+00:00, sha 5260773922fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.