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 faster than LibreTranslate/ArgosTranslate.

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
• 200M parameter seq2seq transformer
• 32k separate Sentencepiece vocabs
• Exported for fast inference to CTranslate2 format
• The pytorch model (for use with 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:

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:

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.'

# 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 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 on the Flores200 devtest test set. comet22 with the comet library and the default model. "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