Update readme

README.md

@@ -1,12 +1,6 @@
 # Model Name
 
-This is a multilingually fine-tuned version of NLLB based on [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb) using the text data of MuST-C v1.0 (En -> 8).
-
-## Model Description
-
-- **Model Type**: Sequence-to-Sequence
-- **Languages Supported**: [List of languages]
-- **Fine-tuning Data**: [Description of your dataset]
+This is a multilingually fine-tuned version of [NLLB](https://arxiv.org/abs/2207.04672) based on [nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) using the text data of MuST-C v1.0 (En -> 8).
 
 ## Usage
 
@@ -16,9 +10,16 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 tokenizer = AutoTokenizer.from_pretrained("johntsi/nllb-200-distilled-600M_mustc_en-to-8")
 model = AutoModelForSeq2SeqLM.from_pretrained("johntsi/nllb-200-distilled-600M_mustc_en-to-8")
 
-text = "Translate this text"
-inputs = tokenizer(text, return_tensors="pt")
-outputs = model.generate(**inputs)
+model.eval()
+model.to("cuda")
+
+text = "Translate this text to German."
+inputs = tokenizer(text, return_tensors="pt").to("cuda")
+outputs = model.generate(
+    **inputs,
+    num_beams=5,
+    forced_bos_token_id=tokenizer.lang_code_to_id["deu_Latn"]
+)
 translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(translated_text)
 ```