Helsinki-NLP/opus-mt_tiny_kor-eng

Model info

Distilled model from a Tatoeba-MT Teacher: Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28, 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

```python
from transformers import MarianMTModel, MarianTokenizer
model_name = "Helsinki-NLP/opus-mt_tiny_fra-eng"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
tok = tokenizer("2017년 말, 시미노프는 쇼핑 텔레비젼 채널인 QVC에 출연했다.", return_tensors="pt").input_ids
output = model.generate(tok)[0]
tokenizer.decode(output, skip_special_tokens=True)

Benchmarks

testset	BLEU	chr-F
flores200	20.3	50.3

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