import transformers
import torch

encoder_model_name = "cl-tohoku/bert-base-japanese-v2"
decoder_model_name = "openai-community/gpt2"
src_tokenizer = transformers.BertJapaneseTokenizer.from_pretrained(encoder_model_name)
trg_tokenizer = transformers.PreTrainedTokenizerFast.from_pretrained(decoder_model_name)
model = transformers.EncoderDecoderModel.from_pretrained("sappho192/jesc-ja-en-translator")


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=512)[0, 1:-1]
    text_trg = trg_tokenizer.decode(output.cpu())
    return text_trg

texts = [
    "逃げろ!",  # Should be "run!"
    "初めまして.",  # "nice to meet you."
    "よろしくお願いします.",  # "thank you."
    "夜になりました",  # "and then it got dark."
    "ご飯を食べましょう."  # "let's eat."
 ]

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

@ARTICLE{pryzant_jesc_2017,
   author = {{Pryzant}, R. and {Chung}, Y. and {Jurafsky}, D. and {Britz}, D.},
    title = "{JESC: Japanese-English Subtitle Corpus}",
  journal = {ArXiv e-prints},
archivePrefix = "arXiv",
   eprint = {1710.10639},
 keywords = {Computer Science - Computation and Language},
     year = 2017,
    month = oct,
}