This model is a pretrained checkpoint and is suitable for fine-tuning on a large dataset. For general use cases, using ElanMT-BT-ja-en is strongly recommended.

This is a translation model based on Marian MT 6-layer encoder-decoder transformer architecture with sentencepiece tokenizer.

The translated result may be very incorrect, harmful or biased. The model was developed to investigate achievable performance with only a relatively small, licensed corpus, and is not suitable for use cases requiring high translation accuracy. Under Section 5 of the CC BY-SA 4.0 License, ELAN MITSUA Project / Abstract Engine is not responsible for any direct or indirect loss caused by the use of the model.