Add application file

app.py

@@ -1,190 +0,0 @@
-import gradio as gr
-import transformers
-from transformers import pipeline
-import PyPDF2
-import pdfplumber
-from pdfminer.high_level import extract_pages, extract_text
-from pdfminer.layout import LTTextContainer, LTChar, LTRect, LTFigure
-import re
-import torch
-from datasets import load_dataset
-import soundfile as sf
-from IPython.display import Audio
-import numpy as np
-from datasets import load_dataset
-import sentencepiece as spm
-import os
-import tempfile
-
-
-
-def text_extraction(element):
-    # Extracting the text from the in-line text element
-    line_text = element.get_text()
-
-    # Find the formats of the text
-    # Initialize the list with all the formats that appeared in the line of text
-    line_formats = []
-    for text_line in element:
-        if isinstance(text_line, LTTextContainer):
-            # Iterating through each character in the line of text
-            for character in text_line:
-                if isinstance(character, LTChar):
-                    # Append the font name of the character
-                    line_formats.append(character.fontname)
-                    # Append the font size of the character
-                    line_formats.append(character.size)
-    # Find the unique font sizes and names in the line
-    format_per_line = list(set(line_formats))
-
-    # Return a tuple with the text in each line along with its format
-    return (line_text, format_per_line)
-
-def read_pdf(pdf_pathy):
-  # create a PDF file object
-  pdfFileObj = open(pdf_pathy, 'rb')
-  # create a PDF reader object
-  pdfReaded = PyPDF2.PdfReader(pdfFileObj)
-
-  # Create the dictionary to extract text from each image
-  text_per_pagy = {}
-  # We extract the pages from the PDF
-  for pagenum, page in enumerate(extract_pages(pdf_pathy)):
-      print("Elaborating Page_" +str(pagenum))
-      # Initialize the variables needed for the text extraction from the page
-      pageObj = pdfReaded.pages[pagenum]
-      page_text = []
-      line_format = []
-      page_content = []
-
-      # Open the pdf file
-      pdf = pdfplumber.open(pdf_pathy)
-
-
-      # Find all the elements
-      page_elements = [(element.y1, element) for element in page._objs]
-      # Sort all the elements as they appear in the page
-      page_elements.sort(key=lambda a: a[0], reverse=True)
-
-      # Find the elements that composed a page
-      for i,component in enumerate(page_elements):
-          # Extract the position of the top side of the element in the PDF
-          pos= component[0]
-          # Extract the element of the page layout
-          element = component[1]
-
-          # Check if the element is a text element
-          if isinstance(element, LTTextContainer):
-              # Check if the text appeared in a table
-                  # Use the function to extract the text and format for each text element
-                  (line_text, format_per_line) = text_extraction(element)
-                  # Append the text of each line to the page text
-                  page_text.append(line_text)
-                  # Append the format for each line containing text
-                  line_format.append(format_per_line)
-                  page_content.append(line_text)
-          
-
-      # Create the key of the dictionary
-      dctkey = 'Page_'+str(pagenum)
-      # Add the list of list as the value of the page key
-      text_per_pagy[dctkey]= [page_text, line_format, page_content]
-
-  # Closing the pdf file object
-  pdfFileObj.close()
-
-
-  return text_per_pagy
-
-#performing a cleaning of the contents
-import re
-
-def clean_text(text):
-    # remove extra spaces
-    text = re.sub(r'\s+', ' ', text)
-
-    return text.strip()
-
-
-def extract_abstract(text_per_pagy):
-    abstract_text = ""
-    
-    #iterate through each page in the extracted text dictionary
-    for page_num, page_text in text_per_pagy.items():
-        if page_text:
-           # Replace hyphens used for line breaks
-            page_text = page_text.replace("- ", "")
-           
-            # Looking for the start of the abstract
-            start_index = page_text.find("Abstract")
-            if start_index != -1:
-                # Adjust the start index to exclude the word "Abstract" itself
-                # The length of "Abstract" is 8 characters; we also add 1 to skip the space after it
-                start_index += len("Abstract") + 1
-
-                # Searching the possible end markers of the abstract
-                end_markers = ["Introduction", "Summary", "Overview", "Background"]
-                end_index = -1
-
-                for marker in end_markers:
-                    temp_index = page_text.find(marker, start_index)
-                    if temp_index != -1:
-                        end_index = temp_index
-                        break
-
-                # If no end marker found, take entire text after "Abstract"
-                if end_index == -1:
-                    end_index = len(page_text)
-
-                # Extract the abstract text
-                abstract = page_text[start_index:end_index].strip()
-
-                # Add the abstract to the complete text
-                abstract_text += " " + abstract
-
-                break
-
-    return abstract_text
-
-
-def main_function(uploaded_filepath):
-    #a control to see if there is a file uploaded
-    if uploaded_filepath is None:
-        return "No file loaded", None
-
-    #read and process the file
-    text_per_pagy = read_pdf(uploaded_filepath)
-
-    #cleaning the text and getting the abstract
-    for key, value in text_per_pagy.items():
-        cleaned_text = clean_text(' '.join(value[0]))
-        text_per_pagy[key] = cleaned_text
-    abstract_text = extract_abstract(text_per_pagy)
-
-    #abstract summary
-    summarizer = pipeline("summarization", model="pszemraj/long-t5-tglobal-base-sci-simplify-elife")
-    summary = summarizer(abstract_text, max_length=50, min_length=30, do_sample=False)[0]['summary_text']
-
-    #generating the audio from the text, with my pipeline and model
-    synthesiser = pipeline("text-to-speech", model="microsoft/speecht5_tts")
-    embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
-    speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
-    speech = synthesiser(summary, forward_params={"speaker_embeddings": speaker_embedding})
-
-    #saving the audio in a temp file
-    audio_file_path = "summary.wav"
-    sf.write(audio_file_path, speech["audio"], samplerate=speech["sampling_rate"])
-
-    #the function returns the 2 pieces we need
-    return summary, audio_file_path
-
-
-iface = gr.Interface(
-    fn=main_function,
-    inputs=gr.File(type="filepath"),  # Cambiato da "pdf" a "file"
-    outputs=[gr.Textbox(label="Summary Text"), gr.Audio(label="Summary Audio", type="filepath")]
-)
-
-# Avvia l'app
-if __name__ == "__main__":
-    iface.launch()