quickmt/quickmt-he-en

<a href="https://huggingface.co/spaces/quickmt/quickmt-gui"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Spaces"></a>

quickmt-he-en Neural Machine Translation Model

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

Try it on our Huggingface Space

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

Model Information

• —Trained using `eole`
• —200M parameter transformer 'big' with 8 encoder layers and 2 decoder layers
• —32k separate Sentencepiece vocabs
• —Exported for fast inference to CTranslate2 format
• —Training data: https://huggingface.co/datasets/quickmt/quickmt-train.he-en/tree/main

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.

git clone https://github.com/quickmt/quickmt.git
pip install ./quickmt/

Finally, use the model in python:

from quickmt import Translator
from huggingface_hub import snapshot_download

# Download Model (if not downloaded already) and return path to local model
# Device is either 'auto', 'cpu' or 'cuda'
t = Translator(
    snapshot_download("quickmt/quickmt-he-en", ignore_patterns="eole-model/*"),
    device="cpu"
)

# Translate - set beam size to 1 for faster speed (but lower quality)
sample_text = '"דר אהוד אור, פרופסור לרפואה באוניברסיטת דלהאוזי בהליפקס, נובה סקוטיה וראש המחלקה הקלינית והמדעית של ארגון חקר הסוכרת הקנדי הזהיר שהמחקר עדיין בימיו הראשונים."'

t(sample_text, beam_size=5)

'"Dr. Ehud Orr, professor of medicine at Dalhousie University in Halifax, Nova Scotia and head of the clinical and scientific department of the Canadian Diabetes Research Organization warned that the study was still in its early days."'

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

'"Deutschland Institute Professor in Medicine at Dalhousie University in Halifax, Nova Scotia, head of Clinical and Scientific Department of the Canadian Diabetes Research Organisation has warned that research was in its early days."'

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 ("hebHebr"->"engLatn"). 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.