~ app.py

app.py

@@ -12,6 +12,8 @@ model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
 def translate(text, num_beams=4, num_return_sequences=4):
   inputs = tokenizer(text, return_tensors="pt")
 
+  num_return_sequences = min(num_return_sequences, num_beams)
+
   translated_tokens = model.generate(
       **inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang], num_beams=num_beams, num_return_sequences=num_return_sequences
   )