has anyone managed to translate something using Helsinki-NLP and ONNX Runtime in Java? Using a Python script, I generated these files:
├── encoder_model.onnx
├── decoder_model.onnx
├── decoder_with_past_model.onnx
├── config.json
├── generation_config.json
├── tokenizer_config.json
├── special_tokens_map.json
├── source.spm
└── target.spm
Then I try to run it in Java like this:
OrtSession.SessionOptions opts = new OrtSession.SessionOptions();
// 2. Load models
System.out.println("Loading encoder and decoder...");
OrtSession encoder = env.createSession(modelDir + "/encoder_model.onnx", opts);
OrtSession decoder = env.createSession(modelDir + "/decoder_model.onnx", opts);
// 3. Tokenizer
HuggingFaceTokenizer tokenizer = HuggingFaceTokenizer.newInstance(modelDir);
But the problem is that there is no tokenizer.json, and the tokenizer tries to download it from Hugging Face, which results in a 404 — I don’t know how to create tokenizer.json.
Or maybe there is some other simpler way to use this model in Java?
