---
title: opus-mt-en-zh
canonical_url: "https://www.modelscope.cn/models/Xenova/opus-mt-en-zh"
md_url: "https://www.modelscope.cn/models/Xenova/opus-mt-en-zh.md"
repository: Xenova/opus-mt-en-zh
last_updated: 2025-07-15
pipeline_tag: translation
tasks:
  - translation
model_type:
  - marian
architectures:
  - MarianMTModel
base_model:
  - Helsinki-NLP/opus-mt-en-zh
base_model_relation: finetune
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
downloads: 1821
stars: 1
---

# opus-mt-en-zh

> opus-mt-en-zh - Xenova 在 ModelScope 开源的模型。https://huggingface.co/Helsinki-NLP/opus-mt-en-zh with ONNX weights to be compatible with Transformers.js.

Xenova/opus-mt-en-zh 是 ModelScope 魔搭社区上的translation模型，基于 Helsinki-NLP/opus-mt-en-zh 构建。

- **Repository**: Xenova/opus-mt-en-zh
- **Tasks**: translation
- **Base model**: Helsinki-NLP/opus-mt-en-zh
- **Downloads**: 1821
- **Stars**: 1
- **Last updated**: 2025-07-15

Source: https://www.modelscope.cn/models/Xenova/opus-mt-en-zh

---

https://huggingface.co/Helsinki-NLP/opus-mt-en-zh with ONNX weights to be compatible with Transformers.js.

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).