ONNX export of
Helsinki-NLP/opus-mt-de-ar for on-device inference on Android.
Download the files and run inference with
ONNX Runtime for Android.
Encoder input: input_ids, attention_mask
Encoder output: encoder_hidden_states
Decoder input: decoder_input_ids, encoder_hidden_states, encoder_attention_mask
Decoder output: logits
Run the encoder once per sentence, then loop the decoder to generate tokens until the EOS token is produced.
Original model by
Helsinki-NLP, trained on
OPUS data.
ONNX conversion by [YOUR_NAME].
CC-BY 4.0 — same as the original model.
