Update app.py

app.py

@@ -1,3 +1,4 @@
+# Import Dependencies
 from PyPDF2 import PdfReader
 from transformers import pipeline, SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
 import torch
@@ -8,10 +9,12 @@ import gradio as gr
 import os, re
 import shutil
 
+# Gradio needs a tmp directory for file store, creating manually
 import os
 path = '/tmp/gradio/tmp1biredw9' 
 os.makedirs(path, exist_ok=True)
 
+# Loading HuggingFace models
 first_model = pipeline(task='summarization',model='pszemraj/long-t5-tglobal-base-16384-book-summary')
 processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
 model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
@@ -19,10 +22,10 @@ model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
 def readAbstract(pdf):
   # Extract text from PDF
   reader = PdfReader(pdf)
-  # Extract each page to variable.
+  # Extract needed page to variable.
   abstract = reader.pages[0]
   abstract = abstract.extract_text()
-  # Removing all before 'abstract' for cleaning
+  # Removing all before 'Abstract' for cleaning
   abstract = abstract[abstract.find('Abstract'):]
   abstract = abstract.split('Introduction', 1)[0]
   return abstract
@@ -42,12 +45,14 @@ def abstract_summary(file):
     abstract = str(abstract)
     abstract = abstract.replace("[","").replace("]","").replace("{","").replace("}","").replace("'","").replace("summary_text: ","")
 
+    # Text to Speech model
     inputs = processor(text=str(abstract), return_tensors="pt")
     embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
     speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
     spectrogram = model.generate_speech(inputs["input_ids"], speaker_embeddings)
     vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
 
+    # Create .wav audio file from above
     with torch.no_grad():
       speech = vocoder(spectrogram)
     speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)