README.md

---
language:
- fr
- en
tags:
- translation
license: cc-by-4.0
datasets:
- quickmt/quickmt-train.fr-en
- quickmt/madlad400-en-backtranslated-fr
- quickmt/newscrawl2024-en-backtranslated-fr
- quickmt/canadian_hansard
model-index:
- name: quickmt-fr-en
  results:
  - task:
      name: Translation fra-eng
      type: translation
      args: fra-eng
    dataset:
      name: flores101-devtest
      type: flores_101
      args: fra_Latn eng_Latn devtest
    metrics:
    - name: BLEU
      type: bleu
      value: 46.84
    - name: CHRF
      type: chrf
      value: 69.87
    - name: COMET
      type: comet
      value: 89.4
---


# `quickmt-fr-en` Neural Machine Translation Model 

`quickmt-fr-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `fr` into `en`.

`quickmt` models are roughly 3 times faster for GPU inference than OpusMT models and roughly [40 times](https://huggingface.co/spaces/quickmt/quickmt-vs-libretranslate) faster than [LibreTranslate](https://huggingface.co/spaces/quickmt/quickmt-vs-libretranslate)/[ArgosTranslate](github.com/argosopentech/argos-translate). 


## *UPDATED VERSION!* 

This model was augmented with back-translated data and has improved translation quality!


## Try it on our Huggingface Space

Give it a try before downloading here: https://huggingface.co/spaces/quickmt/QuickMT-Demo


## Model Information

* Trained using [`eole`](https://github.com/eole-nlp/eole) 
* 200M parameter seq2seq transformer
* 32k separate Sentencepiece vocabs
* Exported for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
* The pytorch model (for use with [`eole`](https://github.com/eole-nlp/eole)) is available in this repository in the `eole-model` folder

See the `eole` model configuration in this repository for further details and the `eole-model` for the raw `eole` (pytorch) model.


## Usage with `quickmt`

You must install the Nvidia cuda toolkit first, if you want to do GPU inference.

Next, install the `quickmt` python library and download the model:

```bash
git clone https://github.com/quickmt/quickmt.git
pip install -e ./quickmt/

quickmt-model-download quickmt/quickmt-fr-en ./quickmt-fr-en
```

Finally use the model in python:

```python
from quickmt import Translator

# Auto-detects GPU, set to "cpu" to force CPU inference
mt = Translator("./quickmt-fr-en/", device="auto")

# Translate - set beam size to 1 for faster speed (but lower quality)
sample_text = "Le Dr Ehud Ur, professeur de médecine à l'Université Dalhousie de Halifax (Nouvelle-Écosse) et président de la division clinique et scientifique de l'Association canadienne du diabète, a averti que la recherche en était encore à ses débuts."

mt(sample_text, beam_size=5)
```

> 'Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia and chair of the clinical and scientific division of the Canadian Diabetes Association, warned that research was still in its infancy.'

```python
# Get alternative translations by sampling
# You can pass any cTranslate2 `translate_batch` arguments
mt([sample_text], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9)
```

> 'Dr. Ehud Ur, Professor of Medicine at Dalhousie University in Halifax, Nova Scotia, and Chair of the Clinical & Scientific Division of the Canadian Diabetes Association, warned the research was still in its infancy.'

The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so you can use `ctranslate2` directly instead of through `quickmt`. It is also possible  to get this model to work with e.g. [LibreTranslate](https://libretranslate.com/) which also uses `ctranslate2` and `sentencepiece`. A model in safetensors format to be used with `eole` is also provided.


## Metrics

`bleu` and `chrf2` are calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores). `comet22` with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32.


|                                       |   bleu |   chrf2 |   comet22 |   Time (s) |
|:--------------------------------------|-------:|--------:|----------:|-----------:|
| quickmt/quickmt-fr-en                 |  46.84 |   69.87 |     89.4  |       1.08 |
| Helsinki-NLP/opus-mt-fr-en            |  41.71 |   66.84 |     88.31 |       3.49 |
| facebook/nllb-200-distilled-600M      |  44.05 |   67.81 |     88.48 |      21.52 |
| facebook/nllb-200-distilled-1.3B      |  46.24 |   69.32 |     89.24 |      37.25 |
| facebook/m2m100_418M                  |  36.48 |   63.3  |     85.87 |      18.28 |
| facebook/m2m100_1.2B                  |  41.69 |   66.51 |     88    |      35.1  |
| tencent/HY-MT1.5-1.8B                 |  28.68 |   61.62 |     88.66 |      9     |
| tencent/Hunyuan-MT-7B-fp8             |  35.66 |   64.94 |     89.72 |     22     |
| CohereLabs/aya-expanse-8b (bnb quant) |  45.03 |   69.02 |     90.29 |     73.97  |