Create app.py

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+from PyPDF2 import PdfFileReader
+from transformers import pipeline
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_path):
+    with open(pdf_path, 'rb') as file:
+        pdf_reader = PdfFileReader(file)
+        text = ""
+        for page_num in range(pdf_reader.numPages):
+            page = pdf_reader.getPage(page_num)
+            text += page.extractText()
+        return text
+
+# Function to extract the abstract from the text
+def extract_abstract(text):
+    abstract = ""
+    found_abstract = False
+    paragraphs = text.split('\n')
+    for index, paragraph in enumerate(paragraphs):
+        if 'Abstract' in paragraph:
+            found_abstract = True
+            abstract = paragraphs[index + 1]  # Get the next paragraph as the abstract
+    return abstract if found_abstract else "Abstract not found"
+
+# Function to summarize text
+def summarize_text(text):
+    summarizer = pipeline("summarization", model="ainize/bart-base-cnn")
+    summarized_text = summarizer(text, max_length=50, min_length=5, do_sample=False)[0]['summary_text']
+    return summarized_text
+
+# Function to convert text to speech
+def text_to_speech(text):
+    from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech
+    processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+    model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+    inputs = processor(text, return_tensors="pt")
+    speech = model.generate_speech(inputs["input_ids"])
+    return speech.numpy().tobytes(), 16000  # Return audio data and sample rate
+
+# Gradio interface
+iface = gr.Interface(
+    fn=lambda pdf_file: text_to_speech(summarize_text(extract_abstract(extract_text_from_pdf(pdf_file.name)))),
+    inputs=gr.File(label="Upload PDF", type="file"),
+    outputs="audio",
+    live=True,
+    title="PDF Abstract Summarizer with Text-to-Speech",
+    description="Upload a PDF, and I will extract the abstract, summarize it, and convert it to speech."
+)
+
+# Launch the interface
+iface.launch()