Create app.py

app.py

@@ -0,0 +1,65 @@
+import torch
+import PyPDF2
+import gradio as gr
+from IPython.display import Audio, display
+from transformers import pipeline 
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import numpy as np
+import scipy
+from gtts import gTTS
+from io import BytesIO
+
+def extract_text(article):
+    pdfReader = PyPDF2.PdfReader(article)
+    pageObj = pdfReader.pages[0]
+    return pageObj.extract_text()
+
+def summarize_abstract(text):
+    sentences = text.split(". ")
+    for i, sentence in enumerate(sentences):
+        if "Abstract" in sentence:
+            start = i + 1
+            end = start + 6
+            break
+    abstract = ". ".join(sentences[start:end+1])
+    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]
+
+    return summary 
+
+def abstract_to_audio(text):
+    tts = gTTS(text, lang='en') 
+    buffer = BytesIO()
+    tts.write_to_fp(buffer)
+    buffer.seek(0)  
+    return buffer.read()
+
+def abstract_audio(article):
+    text = extract_text(article)
+    summary = summarize_abstract(text) 
+    audio = abstract_to_audio(summary)
+    return summary, audio
+
+inputs = gr.File() 
+summary_text = gr.Text()
+audio_summary = gr.Audio()
+
+
+myApp = gr.Interface( fn= abstract_audio, inputs=gr.File(),
+    outputs=[gr.Text(),gr.Audio()], title="Summary of Abstract to Audio ", description="An App that helps you summarises the abstract of an Article\Journal and gives the audio of the summary", examples=["/content/NIPS-2015-hidden-technical-debt-in-machine-learning-systems-Paper.pdf"]
+)
+
+myApp.launch()