from transformers import ( T5Tokenizer, MT5ForConditionalGeneration, Text2TextGenerationPipeline, )

path = "K024/mt5-zh-ja-en-trimmed" pipe = Text2TextGenerationPipeline( model=MT5ForConditionalGeneration.from_pretrained(path), tokenizer=T5Tokenizer.from_pretrained(path), )

sentence = "ja2zh: 吾輩は猫である。名前はまだ無い。" res = pipe(sentence, max_length=100, num_beams=4) res[0]['generated_text']

Training data:

wikimedia-en-ja wikimedia-en-zh wikimedia-ja-zh wikititles-ja-en wikititles-zh-en wikimatrix-ja-zh news-commentary-en-ja news-commentary-en-zh news-commentary-ja-zh ted2020-en-ja ted2020-en-zh ted2020-ja-zh license: other