File size: 3,648 Bytes
b8b16cf 02f8934 cfeeb7f b8b16cf cfeeb7f 8c10b14 cfeeb7f 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 8c10b14 02f8934 8c10b14 02f8934 cfeeb7f 02f8934 cfeeb7f 8c10b14 cfeeb7f 8c10b14 cfeeb7f 8c10b14 cfeeb7f 02f8934 b8b16cf 8c10b14 b8b16cf 02f8934 8c10b14 cfeeb7f 8c10b14 cfeeb7f 8c10b14 02f8934 b8b16cf cfeeb7f b8b16cf cfeeb7f b8b16cf 8c10b14 b8b16cf cfeeb7f b8b16cf 02f8934 b8b16cf cfeeb7f b8b16cf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import gradio as gr
from gtts import gTTS
import pdfplumber
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer
import nltk
import os
# Download NLTK data for sumy
try:
nltk.download('punkt')
nltk.download('punkt_tab')
except Exception as e:
print(f"Error downloading NLTK data: {str(e)}")
def extract_text_from_pdf(pdf_file):
"""
Extract text from a PDF file using pdfplumber.
Args:
pdf_file: Uploaded PDF file.
Returns:
str: Extracted text or error message.
"""
try:
with pdfplumber.open(pdf_file) as pdf:
text = ""
for page in pdf.pages:
page_text = page.extract_text()
if page_text:
text += page_text + " "
return text.strip() if text else "No text could be extracted from the PDF."
except Exception as e:
return f"Error extracting text: {str(e)}"
def summarize_text(text, sentences_count=12):
"""
Summarize text to approximately four paragraphs using sumy LSA summarizer.
Args:
text (str): Text to summarize.
sentences_count (int): Number of sentences in summary (approx. 3 sentences per paragraph).
Returns:
str: Summarized text or error message.
"""
try:
if len(text.split()) < 50:
return "Text is too short to summarize."
parser = PlaintextParser.from_string(text, Tokenizer("english"))
summarizer = LsaSummarizer()
summary = summarizer(parser.document, sentences_count)
summary_text = ""
for i, sentence in enumerate(summary):
summary_text += str(sentence) + " "
if (i + 1) % 3 == 0:
summary_text += "\n\n"
return summary_text.strip() if summary_text else "No summary generated."
except Exception as e:
return f"Error summarizing text: {str(e)}"
def pdf_to_speech(pdf_file, lang="en"):
"""
Convert text from a PDF to summarized speech using gTTS.
Args:
pdf_file: Uploaded PDF file.
lang (str): Language code (default is 'en' for English).
Returns:
tuple: (Path to audio file or None, summarized text or error message).
"""
try:
# Extract text from PDF
text = extract_text_from_pdf(pdf_file)
if "Error" in text:
return None, text
# Summarize text
summarized_text = summarize_text(text, sentences_count=12)
if "Error" in summarized_text or "too short" in summarized_text:
return None, summarized_text
# Create gTTS object
tts = gTTS(text=summarized_text, lang=lang, slow=False)
# Save the audio file
output_file = "output.mp3"
tts.save(output_file)
return output_file, summarized_text
except Exception as e:
return None, f"An error occurred: {str(e)}"
# Define Gradio interface
demo = gr.Interface(
fn=pdf_to_speech,
inputs=[
gr.File(label="Upload a PDF file", file_types=[".pdf"]),
gr.Dropdown(choices=["en", "es", "fr"], label="Select Language", value="en")
],
outputs=[
gr.Audio(label="Generated Speech"),
gr.Textbox(label="Summarized Text")
],
title="PDF Summary to Speech",
description="Upload an English PDF file, select a language, and generate speech from a summarized version (approx. 4 paragraphs). The summarized text is also displayed."
)
# Launch the app
if __name__ == "__main__":
demo.launch() |