genai-content-studio / models /summarizer.py
rahulhans's picture
Upload 15 files
a26e606 verified
import torch
from transformers import BartForConditionalGeneration, BartTokenizer
class TextSummarizer:
def __init__(self):
print("Initializing Text Summarizer...")
self.device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using device: {self.device}")
# Load model and tokenizer
self.model_name = "facebook/bart-large-cnn"
self.tokenizer = BartTokenizer.from_pretrained(self.model_name)
self.model = BartForConditionalGeneration.from_pretrained(self.model_name).to(self.device)
print(f"Loaded {self.model_name} model and moved to {self.device}")
def summarize(self, text, max_length=130, min_length=30):
try:
# Tokenize the input text
inputs = self.tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
inputs = inputs.to(self.device)
# Generate summary
summary_ids = self.model.generate(
inputs["input_ids"],
max_length=max_length,
min_length=min_length,
num_beams=4,
length_penalty=2.0,
early_stopping=True
)
# Decode the generated summary
summary = self.tokenizer.decode(summary_ids[0], skip_special_tokens=True)
return summary
except Exception as e:
return f"Error generating summary: {str(e)}"