Output only showing <unk> tags

I just trained a translation model it ran successfully. But when I am tranlating using that model it is just showing unk tags. Can Anyone tell me what am i doing wrong. The output seems something like that.
<unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk> <unk>

This probably means your model was not trained properly.
You might want to give more details about what you’re trying to achieve and what you’ve done (task, data, config, etc.) if you want people to help.

i am using the default config given for the translation using the transformer model in the official documentation only.