Update app.py

app.py

@@ -1,7 +1,105 @@
+
+#libraries
+from transformers import pipeline  # Import the pipeline function from transformers
+from PyPDF2 import PdfReader
+import torch
+from bark import SAMPLE_RATE, generate_audio, preload_models
+from scipy.io.wavfile import write as write_wav
+from IPython.display import Audio
 import gradio as gr
 
-def greet(name):
-    return "Hello " + name + "!!"
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+def summarize_abstract_from_pdf(pdf_file_path):
+    # Initialize the summarization pipeline
+
+    abstract_string = 'abstract'
+    found_abstract = False
+    intro_string ='introduction'
+    extracted_text_string =""
+
+    # Read the PDF and extract text from the first page
+    with open(pdf_file_path, 'rb') as pdf_file:
+        reader = PdfReader(pdf_file)
+        text = ""
+        text += reader.pages[0].extract_text()
+
+
+    file = text.splitlines()
+    for lines in file:
+      lower_lines = lines.lower()
+      if lower_lines.strip()== abstract_string:
+        found_abstract = True
+      elif "1" in lower_lines.strip() and intro_string in lower_lines.strip():
+        found_abstract = False
+
+      if found_abstract == True:
+        extracted_text_string += lines
+
+
+    extracted_text_string = extracted_text_string.replace("Abstract", "")
+    summarizer = pipeline("summarization", "pszemraj/led-base-book-summary",device=0 if torch.cuda.is_available() else -1,)
+    # Generate a summarized abstract using the specified model
+    summarized_abstract = summarizer(extracted_text_string,
+    min_length=16,
+    max_length=150,
+    no_repeat_ngram_size=3,
+    encoder_no_repeat_ngram_size=3,
+    repetition_penalty=3.5,
+    num_beams=4,
+    early_stopping=True,
+    )
+    #I run this twice to get summazired text
+    summarized_abstract2 = summarizer(summarized_abstract[0]['summary_text'],
+    min_length=16,
+    max_length=25,
+    no_repeat_ngram_size=3,
+    encoder_no_repeat_ngram_size=3,
+    repetition_penalty=3.5,
+    num_beams=4,
+    early_stopping=True,
+    )
+
+
+
+    # Return the summarized abstract as a string
+    return summarized_abstract2[0]['summary_text']
+
+def generate_audio(pdf_file_path):
+    model_name = "suno/bark-small"
+
+    # Download and load the specified model
+    preload_models(model_name)
+
+    # Generate audio from text
+    #call the summarize abstract function
+    text_prompt =  summarize_abstract_from_pdf(pdf_file_path)
+    audio_array = generate_audio(text_prompt)
+ 
+    # Create a temporary WAV file to save the audio
+    with NamedTemporaryFile(suffix=".wav", delete=False) as temp_wav_file:
+        wav_file_path = temp_wav_file.name
+        write_wav(wav_file_path, SAMPLE_RATE, audio_array)
+
+    # Return the path to the saved audio file
+    return wav_file_path
+
+
+
+# Define app name, app description, and examples
+app_name = "PDF to Audio Converter"
+app_description = "Convert text from a PDF file to audio. We only accept pdf formats"
+examples = [
+    ["path/to/pdf/file1.pdf"],
+    ["path/to/pdf/file2.pdf"],
+]
+
+# Create the Gradio app
+demo = gr.Interface(
+    fn=generate_audio,
+    inputs="text",
+    outputs="audio",
+    title=app_name,
+    description=app_description,
+    examples=examples
+)
+demo.launch()