Helsinki-NLP/opus-mt_tiny_spa-eng

OPUS-MT-tiny-spa-eng

Distilled model from a Tatoeba-MT Teacher: Tatoeba-MT-models/cat+oci+spa-eng/opusTCv20210807+bt_transformer-big_2022-03-13, 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_spa-eng"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
tok = tokenizer("La esfinge aparece como escenario de fondo y narradora de una larga historia.", 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+	29.8	59.7	0.8510
Bouquet	43.1	64.4	0.851

Student

testset	BLEU	chr-F	COMET
Flores+	25.0	55.2	0.8300
Bouquet	37.4	60.2	0.8510