Type error: object got multiple values for keyword argument

Question

I am newbee in transformers. Tried to translate generated text from chinese to english and got that issue. Judging from TypeError function got some extra arguments, but i can't understand why. It used to work couple of days ago,but now it doesn't

tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-zh-en",use_fast = False)
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-zh-en")
text = x
tokenized_text = tokenizer.prepare_seq2seq_batch([text], return_tensors='pt')
translation = model.generate(**tokenized_text,return_dict= False)
translated_text = tokenizer.batch_decode(translation, skip_special_tokens=False)[0]

And got :

TypeError                                 Traceback (most recent call last)
<ipython-input-71-f81bc7b071ac> in <module>()
      3 text = x
      4 tokenized_text = tokenizer.prepare_seq2seq_batch([text], return_tensors='pt')
----> 5 translation = model.generate(**tokenized_text,return_dict= False)
      6 translated_text = tokenizer.batch_decode(translation, skip_special_tokens=False)[0]

2 frames
/usr/local/lib/python3.7/dist-packages/transformers/generation_utils.py in _prepare_encoder_decoder_kwargs_for_generation(self, input_ids, model_kwargs)
    412                 argument: value for argument, value in model_kwargs.items() if not argument.startswith("decoder_")
    413             }
--> 414             model_kwargs["encoder_outputs"]: ModelOutput = encoder(input_ids, return_dict=True, **encoder_kwargs)
    415         return model_kwargs
    416 

TypeError: MarianEncoder object got multiple values for keyword argument 'return_dict'