Create app.py

app.py

@@ -0,0 +1,127 @@
+!pip uninstall -y tensorflow
+!pip install tensorflow==2.14
+
+!pip install --upgrade pip
+!pip install --upgrade transformers scipy
+
+!pip install transformers
+!pip install pymupdf
+
+## Summarization
+import gradio as gr
+import fitz  # PyMuPDF
+from transformers import BartTokenizer, BartForConditionalGeneration, pipeline
+import scipy.io.wavfile
+import numpy as np
+
+tokenizer = BartTokenizer.from_pretrained('facebook/bart-large-cnn')
+model = BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')
+
+def extract_abstract(pdf_path):
+    doc = fitz.open(pdf_path)
+    first_page = doc[0].get_text()
+    start_idx = first_page.lower().find("abstract")
+    end_idx = first_page.lower().find("introduction")
+    if start_idx != -1 and end_idx != -1:
+        return first_page[start_idx:end_idx].strip()
+    else:
+        return "Abstract not found or '1 Introduction' not found in the first page."
+
+# Specify the path to your PDF file
+pdf_path = "/content/article11.pdf"  # Update the path
+
+# Extract the abstract
+abstract_text = extract_abstract(pdf_path)
+
+# Print the extracted abstract
+print("Extracted Abstract:")
+print(abstract_text)
+
+
+from IPython.core.display import display, HTML
+
+# Function to display summary and reduction percentage aesthetically
+def display_results(final_summary, original_text):
+    reduction_percentage = 100 * (1 - len(final_summary) / len(original_text))
+    html_content = f"""
+    <div style='padding: 20px; background-color: #f3f3f3; border-radius: 10px;'>
+        <h2 style='color: #2c3e50; text-align: center;'>Summary</h2>
+        <p style='color: #34495e; font-size: 16px; text-align: justify;'>{final_summary}</p>
+        <p style='color: #2c3e50;'><b>Reduction in Text:</b> {reduction_percentage:.2f}%</p>
+    </div>
+    """
+    display(HTML(html_content))
+
+# Summary generation and post-processing
+inputs = tokenizer([abstract_text], max_length=1024, return_tensors='pt', truncation=True)
+max_length_for_summary = 40
+length_penalty_value = 2.0
+
+summary_ids = model.generate(inputs['input_ids'],
+                             num_beams=4,
+                             max_length=max_length_for_summary,
+                             min_length=10,
+                             length_penalty=length_penalty_value,
+                             early_stopping=True,
+                             no_repeat_ngram_size=2)
+
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+summary = ' '.join(summary.split())  # Remove extra spaces
+
+# Handle truncated words and adjust periods
+words = summary.split()
+cleaned_summary = []
+for i, word in enumerate(words):
+    if '-' in word and i < len(words) - 1:
+        word = word.replace('-', '') + words[i + 1]
+        words[i + 1] = ""
+
+    if '.' in word and i != len(words) - 1:
+        word = word.replace('.', '')
+        cleaned_summary.append(word + ' and')
+    else:
+        cleaned_summary.append(word)
+
+# Capitalize first word and adjust following words
+final_summary = ' '.join(cleaned_summary)
+final_summary = final_summary[0].upper() + final_summary[1:]
+final_summary = ' '.join(w[0].lower() + w[1:] if w.lower() != 'and' else w for w in final_summary.split())
+
+# Displaying the results
+display_results(final_summary, abstract_text)
+
+
+##Text-to-Speech
+
+# Initialize the Bark TTS pipeline
+synthesiser = pipeline("text-to-speech", "suno/bark")
+
+# Initialize the Bark TTS pipeline
+synthesiser = pipeline("text-to-speech", "suno/bark")
+
+# Convert the summarized text to speech
+speech = synthesiser(final_summary, forward_params={"do_sample": True})
+
+# Normalize the audio data
+audio_data = speech["audio"].squeeze()
+normalized_audio_data = np.int16(audio_data / np.max(np.abs(audio_data)) * 32767)
+
+# Save the normalized audio data as a WAV file
+output_file = "/content/bark_output.wav"
+scipy.io.wavfile.write(output_file, rate=speech["sampling_rate"], data=normalized_audio_data)
+print(f"Audio file saved as {output_file}")
+
+# Display an audio player widget to play the generated speech
+Audio(output_file)
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=process_text,
+    inputs="text",
+    outputs=["text", "audio"],
+    title="Summarization and Text-to-Speech",
+    description="Enter text to summarize and convert to speech."
+)
+
+if __name__ == "__main__":
+    iface.launch()