File size: 1,782 Bytes
cba2ea4 5f7e3d8 c363ecf cba2ea4 5f7e3d8 c363ecf 5f7e3d8 cba2ea4 c98d7c6 cba2ea4 c98d7c6 cba2ea4 c98d7c6 cba2ea4 c98d7c6 cba2ea4 c98d7c6 cba2ea4 c98d7c6 cba2ea4 b2410fa cba2ea4 |
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 |
import gradio as gr
from PyPDF2 import PdfReader
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from gtts import gTTS
from io import BytesIO
import base64
import re
model_name = "ArtifactAI/led_large_16384_arxiv_summarization"
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
def extract_first_sentence(text):
"""
Extracts the first sentence from the given text.
"""
sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
if sentences:
return sentences[0]
else:
return text
def summarize_pdf_abstract(pdf_file):
"""
Reads a PDF file, extracts the abstract, summarizes it as the first sentence, and generates audio.
"""
try:
reader = PdfReader(pdf_file)
abstract_text = ""
for page in reader.pages:
if "Abstract" in page.extract_text() or "Introduction" in page.extract_text():
abstract_text = page.extract_text()
break
inputs = tokenizer(abstract_text, return_tensors="pt")
outputs = model.generate(**inputs)
summary = tokenizer.decode(outputs[0])
# Extract only the first sentence
summary_sentence = extract_first_sentence(summary)
# Generate audio
speech = gTTS(text=summary_sentence, lang="en")
speech_bytes = BytesIO()
speech.write_to_fp(speech_bytes)
# Encode audio data with Base64
audio_data = base64.b64encode(speech_bytes.getvalue()).decode("utf-8")
# Return individual output values
return summary_sentence, audio_data
except Exception as e:
raise Exception(str(e))
interface = gr.Interface(
fn=summarize_pdf_abstract,
inputs=[gr.File(label="Upload PDF")],
outputs=[gr.Textbox(label="Summary"), gr.Audio()],
)
interface.launch(share=True)
|