Edit model card

FuguMT

This is a translation model using Marian-NMT. For more details, please see my repository.

  • source language: en
  • target language: ja

How to use

This model uses transformers and sentencepiece.

!pip install transformers sentencepiece

You can use this model directly with a pipeline:

from transformers import pipeline
fugu_translator = pipeline('translation', model='staka/fugumt-en-ja')
fugu_translator('This is a cat.')

If you want to translate multiple sentences, we recommend using pySBD.

!pip install transformers sentencepiece pysbd

import pysbd
seg_en = pysbd.Segmenter(language="en", clean=False)

from transformers import pipeline
fugu_translator = pipeline('translation', model='staka/fugumt-en-ja')
txt = 'This is a cat. It is very cute.'
print(fugu_translator(seg_en.segment(txt)))

Eval results

The results of the evaluation using tatoeba(randomly selected 500 sentences) are as follows:

source target BLEU(*1)
en ja 32.7

(*1) sacrebleu --tokenize ja-mecab

Downloads last month
1,834
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using staka/fugumt-en-ja 1