Update app.py

app.py

@@ -1,63 +1,49 @@
+import gradio as gr
+
 from PyPDF2 import PdfReader
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 from gtts import gTTS
-from IPython.display import Audio
+from io import BytesIO
 
-# Download the model and tokenizer
+# Define model and tokenizer
 model_name = "ArtifactAI/led_large_16384_arxiv_summarization"
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-def summarize_pdf_abstract(pdf_path):
+def summarize_pdf_abstract(pdf_data):
     """
     Reads a PDF file, extracts the abstract, and summarizes it in one sentence.
 
     Args:
-      pdf_path: Path to the PDF file.
+        pdf_data: A byte string containing the PDF data.
 
     Returns:
-      A string containing the one-sentence summary of the abstract.
+        A dictionary containing the one-sentence summary of the abstract and the generated audio.
     """
 
-    # Read the PDF file
-    reader = PdfReader(open(pdf_path, 'rb'))
-
-    # Extract the abstract
+    reader = PdfReader(BytesIO(pdf_data))
     abstract_text = ""
+
     for page in reader.pages:
-        # Search for keywords like "Abstract" or "Introduction"
         if "Abstract" in page.extract_text() or "Introduction" in page.extract_text():
-            # Extract the text following the keyword
             abstract_text = page.extract_text()
             break
 
-    # Encode the abstract text
     inputs = tokenizer(abstract_text, return_tensors="pt")
-
-    # Generate the summary
     outputs = model.generate(**inputs)
-
-    # Decode the summary
     summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    return summary
-
-# Define the file path
-pdf_path = "/content/Article 11 Hidden Technical Debt in Machine Learning Systems.pdf"
-
-# Summarize the abstract
-summary = summarize_pdf_abstract(pdf_path)
-
-# Print the summary
-print("One-sentence summary of the abstract:")
-print(summary)
+    speech = gTTS(summary, lang="en")
+    speech_bytes = speech.get_wav_data()
 
-# Choose your preferred language for the audio
-language = "en"
+    return {"summary": summary, "audio": speech_bytes}
 
-# Generate audio file
-speech = gTTS(summary, lang=language)
-speech.save("summary.mp3")
+# Create Gradio interface
+interface = gr.Interface(
+    fn=summarize_pdf_abstract,
+    inputs=[gr.File(label="Upload PDF", mimetypes=["application/pdf"])],
+    outputs=[gr.Text(label="One-sentence summary"), gr.Audio(label="Summary audio")],
+)
 
-# Display the audio file
-Audio("summary.mp3")
+# Launch the Hugging Face Space
+interface.launch(title="PDF Abstract Summarizer")