# Issue with MBart50 translation

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-mbart50-translation%2F3959%3E%5C
**Category:** Beginners\
**Created:** [February 24, 2021, 5:51pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-mbart50-translation%2F3959 "2021-02-24T17:51:39Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![AlanFeder](https://avatars.discourse-cdn.com/v4/letter/a/278dde/32.png) [@AlanFeder](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanFeder)%5C
**Post date:** [February 24, 2021, 5:51pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-mbart50-translation%2F3959%2F1 "2021-02-24T17:51:39Z")

</div>

Hi,

I am having an issue with the new MBart50 - I was wondering if you could help me figure out what I am doing wrong.

I am trying to copy code from [here](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) – specifically, I tweaked it to translate a sentence from French into Persian.

```python
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast

article_fr = "Paris est toujours une bonne idee"

model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")

# translate Hindi to French
tokenizer.src_lang = "fr_XX"
encoded_hi = tokenizer(article_fr, return_tensors="pt")
generated_tokens = model.generate(
    **encoded_hi,
    forced_bos_token_id=tokenizer.lang_code_to_id["fa_IR"]
)
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)

```

but it then outputs

```auto
['Paris is always a good idea']

```

(which is obviously in English – not in Persian)

How can I get it to output in Persian? I tried using the `"fa_IR"` lang\_code\_to\_id.

Thanks

---

<div class="post-metadata">

**Author:** ![neverNull](https://avatars.discourse-cdn.com/v4/letter/n/bcef8e/32.png) [@neverNull](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FneverNull)%5C
**Post date:** [February 24, 2021, 7:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-mbart50-translation%2F3959%2F2 "2021-02-24T19:23:33Z")

</div>

I have the following returned. However, longer strings yield FR results, not 100% sure why. I assume it is a lack of training sentence pairs. Good luck!

> سلام

Returned from this snippet.

```
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast

article_fr = "Bonjour"

model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-one-to-many-mmt")
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-one-to-many-mmt", src_lang="fr_XX")

model_inputs = tokenizer(article_fr, return_tensors="pt")

generated_tokens = model.generate(
    **model_inputs,
    forced_bos_token_id=tokenizer.lang_code_to_id["fa_IR"]
)
print(tokenizer.batch_decode(generated_tokens, skip_special_tokens=True))

```

---

<div class="post-metadata">

**Author:** ![AlanFeder](https://avatars.discourse-cdn.com/v4/letter/a/278dde/32.png) [@AlanFeder](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlanFeder)%5C
**Post date:** [February 24, 2021, 7:44pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissue-with-mbart50-translation%2F3959%2F3 "2021-02-24T19:44:17Z")

</div>

Yes – thanks! I get the same results for “Bonjour” as well.
