opus-mt-tc-big-tr-en doesn't work properly.

[bleriot14]

Hello, I added the code below. It returns strange output. Do you know how can I make work this model right ?

from transformers import AutoTokenizer, MarianMTModel
tokenizer = AutoTokenizer.from_pretrained('2_models\opus-mt-tc-big-tr-en')
inputs = tokenizer("Hey!Birlikte öğrenelim", return_tensors="pt", padding=True)
model = MarianMTModel.from_pretrained('2_models\opus-mt-tc-big-tr-en')
print(tokenizer.batch_decode(model.generate(**inputs)))

it returns "[' connectconnectconneectconnectconnectconnectconnectconnectconnectcoconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnectconnect']"