Helsinki-NLP/opus-mt_tiny_eng-ita

OPUS-MT-tiny-eng-ita

Distilled model from a Tatoeba-MT Teacher: Tatoeba-MT-models/deu+eng+fra+por+spa-itc/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30., which has been trained on the Tatoeba dataset.

We used the OpusDistillery to train new a new student with the tiny architecture, with a regular transformer decoder. For training data, we used Tatoeba. The configuration file fed into OpusDistillery can be found here.

How to run

from transformers import MarianMTModel, MarianTokenizer
model_name = "Helsinki-NLP/opus-mt_tiny_eng-ita"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
tok = tokenizer("The area is also home to species of animals and birds with a wide variety.", return_tensors="pt").input_ids
output = model.generate(tok)[0]
tokenizer.decode(output, skip_special_tokens=True)

Benchmarks

Teacher

testset	BLEU	chr-F	COMET
Flores+	30.6	59.4	0.8600
Bouquet	55.0	74.9	0.8865

Student

testset	BLEU	chr-F	COMET
Flores+	27.6	57.5	0.8410
Bouquet	49.8	71.4	0.8785