Update summarizer.py

summarizer.py

@@ -1,29 +1,16 @@
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, BartTokenizer, BartForConditionalGeneration
+from transformers import BartTokenizer, BartForConditionalGeneration
 
-# Английская модель
-eng_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
-eng_model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
+tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
+model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
 
-# Русская модель (публичная)
-rus_tokenizer = AutoTokenizer.from_pretrained("IlyaGusev/mbart_ru_sum_gazeta")
-rus_model = AutoModelForSeq2SeqLM.from_pretrained("IlyaGusev/mbart_ru_sum_gazeta")
-
-def generate_summary(text: str, lang="en", max_length=200, min_length=50) -> str:
-    if lang == "ru":
-        tokenizer = rus_tokenizer
-        model = rus_model
-    else:
-        tokenizer = eng_tokenizer
-        model = eng_model
-
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=1024)
+def generate_summary(text: str) -> str:
+    inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors="pt")
 
     summary_ids = model.generate(
         inputs["input_ids"],
-        max_length=max_length,
-        min_length=min_length,
-        length_penalty=2.0,
         num_beams=4,
+        min_length=40,
+        max_length=200,
         early_stopping=True
     )