# https://elrmnd-vocal-pdf-summarizer.hf.space

# Import libraries

import gradio as gr
import PyPDF2
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from gtts import gTTS
from io import BytesIO

# Function to extract text from PDF
# Defines a function to extract raw text from a PDF file
def extract_text(pdf_file):
    pdfReader = PyPDF2.PdfReader(pdf_file)
    pageObj = pdfReader.pages[0]
    return pageObj.extract_text()

# Function to summarize text
# Defines a function to summarize the extracted text using facebook/bart-large-cnn
def summarize_text(text):
    sentences = text.split(". ")
    start = -1  # Default value if "Abstract" is not found
    end = -1

    for i, sentence in enumerate(sentences):
        if "Abstract" in sentence:
            start = i + 1
            end = start + 6
            break

    if start != -1:
        abstract = ". ".join(sentences[start:end + 1])

        # Load BART model & tokenizer
        tokenizer = AutoTokenizer.from_pretrained("pszemraj/led-base-book-summary")
        model = AutoModelForSeq2SeqLM.from_pretrained("pszemraj/led-base-book-summary")

        # Tokenize abstract
        inputs = tokenizer(abstract,
                           max_length=1024,
                           return_tensors="pt",
                           truncation=True)

        # Generate summary
        summary_ids = model.generate(inputs['input_ids'],
                                     max_length=50,
                                     min_length=30,
                                     no_repeat_ngram_size=3,
                                     encoder_no_repeat_ngram_size=3,
                                     repetition_penalty=3.5,
                                     num_beams=4,
                                     do_sample=True,
                                     early_stopping=False)

        summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)

        if '.' in summary:
            index = summary.rindex('.')
            if index != -1:
                summary = summary[:index + 1]
    else:
        summary = "Abstract not found in the document."

    return summary

# Function to convert text to audio
# Defines a function to convert text to an audio file using Google Text-to-Speech
def text_to_audio(text):
    tts = gTTS(text, lang='en')
    buffer = BytesIO()
    tts.write_to_fp(buffer)
    buffer.seek(0)
    return buffer.read()

### Main function
### The main function that ties everything together:
### extracts text, summarizes, and converts to audio.
def audio_pdf(pdf_file):
    text = extract_text(pdf_file)
    summary = summarize_text(text)
    audio = text_to_audio(summary)
    return summary, audio

# Define Gradio interface
# Gradio web interface with a file input, text output to display the summary
# and audio output to play the audio file. # Launches the interface
inputs = gr.File()
summary_text = gr.Text()
audio_summary = gr.Audio()

iface = gr.Interface(
    fn=audio_pdf,
    inputs=inputs,
    outputs=[summary_text, audio_summary],
    title="The Vocal PDF Summarizer",
    description="I will summarize only PDFs with an abstract and transform it into audio. If abstract is not present in the document a message will show",
    examples=["Article 11 Hidden Technical Debt in Machine Learning Systems.pdf",
              "Article 6 BloombergGPT_ A Large Language Model for Finance.pdf",
              "Article 5 A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks.pdf",
              "Article 8 Llama 2_ Open Foundation and Fine-Tuned Chat Models.pdf"
             ]
)

iface.launch()  # Launch the interface