HY-MT (Hunyuan Translation) is a high-quality multilingual machine translation model suite developed to support mutual translation across dozens of languages with strong performance even at smaller model scales. It ships with both an 1.8 B parameter model and a larger 7 B model, the latter optimized not only for direct translation but also for formatted and contextualized output, allowing better handling of terminology and mixed-language content. The project emphasizes both speed and quality, with the smaller model able to be quantized and deployed on edge devices for real-time translation tasks without requiring large server infrastructure. Terminology intervention and contextual translation features give users control over how specific terms or styles are rendered, which is important for technical or domain-specific content.

Features

  • Multilingual translation across 30+ languages
  • Compact model designed for edge device inference
  • Contextual translation support
  • Terminology intervention for customized outputs
  • Multiple model sizes (1.8 B and 7 B)
  • Integration via Transformers ecosystem

Project Samples

Project Activity

See All Activity >

Categories

AI Models

License

MIT License

Follow HY-MT

HY-MT Web Site

You Might Also Like
MongoDB Atlas runs apps anywhere Icon
MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of HY-MT!

Additional Project Details

Programming Language

Python

Related Categories

Python AI Models

Registered

2026-01-28