metadata
license: mit
datasets:
- Helsinki-NLP/tatoeba_mt
language:
- ja
- ko
pipeline_tag: translation
tags:
- python
- transformer
- pytorch
Japanese to Korean translator for FFXIV
FINAL FANTASY is a registered trademark of Square Enix Holdings Co., Ltd.
This project is detailed on the Github repo.
Demo
Usage
Check the test_eval.ipynb or below section.
Inference
from transformers import(
EncoderDecoderModel,
PreTrainedTokenizerFast,
BertJapaneseTokenizer,
)
import torch
encoder_model_name = "cl-tohoku/bert-base-japanese-v2"
decoder_model_name = "skt/kogpt2-base-v2"
src_tokenizer = BertJapaneseTokenizer.from_pretrained(encoder_model_name)
trg_tokenizer = PreTrainedTokenizerFast.from_pretrained(decoder_model_name)
# You should change following `./best_model` to the path of model **directory**
model = EncoderDecoderModel.from_pretrained("./best_model")
text = "ギルガメッシュ討伐戦"
# text = "ギルガメッシュ討伐戦に行ってきます。一緒に行きましょうか？"
def translate(text_src):
embeddings = src_tokenizer(text_src, return_attention_mask=False, return_token_type_ids=False, return_tensors='pt')
embeddings = {k: v for k, v in embeddings.items()}
output = model.generate(**embeddings)[0, 1:-1]
text_trg = trg_tokenizer.decode(output.cpu())
return text_trg
print(translate(text))