ArthurZ

/

test-final

like 0

Following the merge of a PR in transformers it appeared that this model was not properly converted. This PR will fix the inference and was tested using the following script:

>>> from transformers import MarianModel, MarianMTModel
>>> tokenizer = AutoTokenizer.from_pretrained(Helsinki-NLP/opus-mt-tc-big-gmw-gmw)
>>> inputs = tokenizer(' >>en<< Hey how are you?', return_tensors=pt, padding=True)
>>> model = MarianMTModel.from_pretrained(Helsinki-NLP/opus-mt-tc-big-gmw-gmw)
>>> print(tokenizer.batch_decode(model.generate(**inputs)))
['<pad> "H Hey, wie geht es dir?"?"????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????</s>']