Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer | |
| import pdfplumber | |
| from docx import Document | |
| import textract | |
| from langdetect import detect | |
| # Function to detect language from the text | |
| def detect_language(text): | |
| try: | |
| return detect(text) | |
| except Exception as e: | |
| print(f"Error detecting language: {e}") | |
| return None | |
| # Function to read document and extract text | |
| def read_document(file_path): | |
| text = "" | |
| try: | |
| if file_path.endswith('.pdf'): | |
| with pdfplumber.open(file_path) as pdf: | |
| for page in pdf.pages: | |
| text += page.extract_text() | |
| elif file_path.endswith('.docx'): | |
| doc = Document(file_path) | |
| for para in doc.paragraphs: | |
| text += para.text | |
| else: | |
| text = textract.process(file_path).decode() | |
| except Exception as e: | |
| print(f"An error occurred: {e}") | |
| return text | |
| # Function to get summarization model | |
| def get_summarizer(language): | |
| model_name = "facebook/bart-large-cnn" if language == "en" else "facebook/mbart-large-50" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForSeq2SeqLM.from_pretrained(model_name) | |
| return pipeline("summarization", model=model, tokenizer=tokenizer) | |
| # Gradio interface function to summarize the document | |
| def summarize_document(file_info): | |
| try: | |
| # Read the uploaded file and extract text | |
| file_path = file_info["name"] | |
| text = read_document(file_path) | |
| if not text.strip(): | |
| return "The document is empty or could not be read." | |
| # Detect the language of the text | |
| language = detect_language(text) | |
| if not language: | |
| return "Language detection failed." | |
| # Get the appropriate summarizer model | |
| summarizer = get_summarizer(language) | |
| # Generate summary | |
| summary = summarizer(text, max_length=130, min_length=30, truncation=True) | |
| return summary[0]['summary_text'] | |
| except Exception as e: | |
| # This will print the error message and the traceback | |
| print(f"An error occurred: {e}") | |
| traceback.print_exc() | |
| return str(e) # Return the error message as output to the user | |
| # Gradio app interface | |
| iface = gr.Interface( | |
| fn=summarize_document, | |
| inputs=gr.File(label="Upload your document (PDF, DOCX, or TXT)", type="binary"), | |
| outputs="text", | |
| title="Document Summarizer", | |
| description="Upload your document and get a summarized version of its content. Currently supports English and French." | |
| ) | |
| # Run the Gradio app | |
| iface.launch() | |