Helsinki-NLP/opus-mt_tiny_ita-eng

OPUS-MT-tiny-ita-eng

Distilled model from a Tatoeba-MT Teacher: OPUS-MT-models/it-en/opus-2019-12-18, 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 pipeline
>>> pipe = pipeline("translation", model="Helsinki-NLP/opus-mt_tiny_ita-eng", max_length=256)
>>> pipe("Ciao, come sta?")

Benchmarks

Teacher

testset	BLEU	chr-F	COMET
Flores+	29.4	60.0	0.8416
Bouquet	52.4	70.3	0.8824

Student

testset	BLEU	chr-F	COMET
Flores+	-	-	-
Bouquet	-	-	-

Marian models

We also provide Marian-compatible versions of this model. To use them, compile Marian and run decoding with marian-decoder, for example:

marian-decoder \
  -i input.txt \
  -c final.model.npz.best-perplexity.npz.decoder.yml \
  -m final.model.npz.best-perplexity.npz \
  -v vocab.spm vocab.spm