#113113th of 126 in ML frameworks and libraries
argos-translate
Offline machine translation library for Python, built on OpenNMT
- Stars
- 6.6k
- License
- MIT
- Last commit
- Aug 2026
- Last release
- Aug 2021
- Language
- Python
5,756 on 4 Apr 20266,617 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Argos Translate translates text offline using OpenNMT models run through CTranslate2. It works as a Python library, a command-line tool (argospm, argos-translate) or a separate GUI, and installs language models as .argosmodel packages. When no direct pair is installed, it pivots through an intermediate language, such as es to en to fr, at some cost in quality.
Who it is for: Developers needing local, offline text translation in Python or scripts
Strengths
- Runs fully offline once language packages are installed
- Installs with pip; usable from Python, CLI or GUI
- Automatic pivoting through intermediate languages covers pairs without a direct model
- Optional GPU via ARGOS_DEVICE_TYPE=cuda or auto, passed to CTranslate2
Weaknesses
- Last tagged release is 2021-08-24, though commits continue
- Pivot translations lose quality compared with direct pairs
- GUI, HTML and file translation live in separate repositories
- Custom models cost $1000 per language, per the README
What it needs
- GPU optional
- Needs OpenNMT, CTranslate2
- Models: .argosmodel packages (OpenNMT)
Quick answers
Is argos-translate open source?
Yes. Its code is on GitHub under the MIT license.
Does argos-translate need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in ML frameworks and libraries
See all 126| Rank | Project | Score |
|---|---|---|
| 1 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 95 out of 100 |
| 2 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |