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

👁 demo.gif
Click to try demo 👁 demo2.gif
Check this Windows app demo with ONNX model

Usage

Inference (PyTorch)

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, max_length=500)[0, 1:-1]
 text_trg = trg_tokenizer.decode(output.cpu())
 return text_trg

print(translate(text))

Inference (Optimum.OnnxRuntime)

Note that current Optimum.OnnxRuntime still requires PyTorch for backend. [Issue] You can use either [ONNX] or [quantized ONNX] model.

from transformers import BertJapaneseTokenizer,PreTrainedTokenizerFast
from optimum.onnxruntime import ORTModelForSeq2SeqLM
from onnxruntime import SessionOptions
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)

sess_options = SessionOptions()
sess_options.log_severity_level = 3 # mute warnings including CleanUnusedInitializersAndNodeArgs
# change subfolder to "onnxq" if you want to use the quantized model
model = ORTModelForSeq2SeqLM.from_pretrained("sappho192/ffxiv-ja-ko-translator",
 sess_options=sess_options, subfolder="onnx") 

texts = [
 "逃げろ!", # Should be "도망쳐!"
 "初めまして.", # "반가워요"
 "よろしくお願いします.", # "잘 부탁드립니다."
 "ギルガメッシュ討伐戦", # "길가메쉬 토벌전"
 "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？", # "길가메쉬 토벌전에 갑니다. 같이 가실래요?"
 "夜になりました", # "밤이 되었습니다"
 "ご飯を食べましょう." # "음, 이제 식사도 해볼까요"
 ]


def translate(text_src):
 embeddings = src_tokenizer(text_src, return_attention_mask=False, return_token_type_ids=False, return_tensors='pt')
 print(f'Src tokens: {embeddings.data["input_ids"]}')
 embeddings = {k: v for k, v in embeddings.items()}

 output = model.generate(**embeddings, max_length=500)[0, 1:-1]
 print(f'Trg tokens: {output}')
 text_trg = trg_tokenizer.decode(output.cpu())
 return text_trg


for text in texts:
 print(translate(text))
 print()

Training

Check the training.ipynb.