Update README.md

README.md

@@ -17,6 +17,9 @@ To force the target language id as the first generated token, pass the `forced_b
 *Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
 To install `sentencepiece` run `pip install sentencepiece`
 
+Since the model was trained with domain tags, you should prepend them to the input as well.
+* "wmtdata newsdomain": Use for sentences in the news domain
+* "wmtdata otherdomain": Use for sentences in all other domain
 
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
@@ -26,14 +29,14 @@ tokenizer = AutoTokenizer.from_pretrained("facebook/wmt21-dense-24-wide-x-en")
 
 # translate German to English
 tokenizer.src_lang = "de"
-inputs = tokenizer("Ein Modell für viele Sprachen", return_tensors="pt")
+inputs = tokenizer("wmtdata newsdomain Ein Modell für viele Sprachen", return_tensors="pt")
 generated_tokens = model.generate(**inputs)
 tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
 # => "A model for many languages"
 
 # translate Icelandic to English
 tokenizer.src_lang = "is"
-inputs = tokenizer("Ein fyrirmynd fyrir mörg tungumál", return_tensors="pt")
+inputs = tokenizer("wmtdata newsdomain Ein fyrirmynd fyrir mörg tungumál", return_tensors="pt")
 generated_tokens = model.generate(**inputs)
 tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
 # => "One model for many languages"