---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-fr
library_name: transformers
pipeline_tag: translation
tags:
- translation
- marian
---

# translate-en-fr

> Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-en-fr

Machine translation model, `en` to `fr`, published by Windstorm Labs.

## Attribution

Derived from [`Helsinki-NLP/opus-mt-en-fr`](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr), licensed **apache-2.0**.
Windstorm Labs did not train the original model. This notice provides the attribution the
licence requires.

## What was changed

**The weights in this repository have been modified from the original.** A LoRA fine-tune trained on parallel corpus data and merged into the base weights.

| | |
|---|---|
| Method | `windy-hallmark` |
| Tensors modified | **36 of 254** |
| Max absolute weight delta | **7.423e-05** |
| Verified | tensor-by-tensor against the upstream original, 2026-07-26 |

The comparison is tensor-level rather than file-level: safetensors and PyTorch `.bin`
containers hash differently even when the tensors inside are identical, so a file-hash
mismatch would prove nothing.

## Contents

A single transformers build in safetensors format, loadable directly:

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tok = AutoTokenizer.from_pretrained("WindyTranslate/translate-en-fr")
model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-en-fr")

batch = tok(["<your text here>"], return_tensors="pt", padding=True)
print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True))
```

Other builds of this pair, including CTranslate2 INT8, are not included in this repository.

## Evaluation

| Benchmark | chrF++ | BLEU | Band |
|---|---:|---:|---|
| FLORES-200 dev, 48 sentences (English → French) | 66.23 | 45.65 | Excellent |

Measured 2026-08-04; screening score, not a publication result. Bands: Excellent ≥60, Good 45–60, Usable 30–45, Limited 15–30, Not recommended <15 (chrF++).

## Limitations

- A single language direction: `en` to `fr`.
- The evaluation above is a 48-sentence screening score, not a publication result. The weights are
  verified to differ from the original; that is a statement about provenance.
- Quality is not monotonic with model size or with the amount of fine-tuning applied.