Create app.py

app.py

@@ -0,0 +1,99 @@
+# https://huggingface.co/spaces/gigisan81/lg_assessment3
+
+# Here are the imports
+import gradio as gr
+from transformers import pipeline
+from tempfile import NamedTemporaryFile
+from PyPDF2 import PdfReader
+from IPython.display import Audio
+import numpy as np
+from bark import SAMPLE_RATE, generate_audio, preload_models
+from scipy.io.wavfile import write as write_wav
+import torch
+# Here is the code
+def summarize_abstract_from_pdf(pdf_file_path):
+    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_func(pdf_file):
+    
+    pdf_file_path = pdf_file.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, 22050, (audio_array * 32767).astype(np.int16))
+    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. Upload a PDF file. We accept only PDF files with abstracts."
+
+# Create the Gradio app
+input_component = gr.File(file_types=["pdf"])
+output_component = gr.Audio()
+
+demo = gr.Interface(
+    fn=generate_audio_func,
+    inputs=input_component,
+    outputs=output_component,
+    title=app_name,
+    description=app_description
+)
+
+demo.launch()