Update app.py

app.py

@@ -1,30 +1,26 @@
+# to create nueral network
 import torch
+
+# for interface
 import gradio as gr
+
+# to open images
 from PIL  import Image
+
+# used for audio
 import scipy.io.wavfile as wavfile
 
 # Use a pipeline as a high-level helper
 from transformers import pipeline
 
-# from phonemizer.backend.espeak.wrapper import EspeakWrapper
-# _ESPEAK_LIBRARY = '/opt/homebrew/Cellar/espeak/1.48.04_1/lib/libespeak.1.1.48.dylib'  #use the Path to the library.
-# EspeakWrapper.set_library(_ESPEAK_LIBRARY)
 
 device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
 
 narrator = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
 
-# tts_model_path = "../Models/models--kakao-enterprise--vits-ljs/snapshots/3bcb8321394f671bd948ebf0d086d694dda95464"
-
-# narrator = pipeline("text-to-speech", model=tts_model_path) 
-
 # Load the pretrained weights
 caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large", device=device)
 
-# model_path = "../Models/models--Salesforce--blip-image-captioning-large/snapshots/2227ac38c9f16105cb0412e7cab4759978a8fd90"
-
-# Load the pretrained weights
-# caption_image = pipeline("image-to-text", model=model_path, device=device)
 
 # Define the function to generate audio from text 
 def generate_audio(text):
@@ -36,13 +32,13 @@ def generate_audio(text):
                   data=narrated_text["audio"][0])
 
     # Return the path to the saved output WAV file
-    return "output.wav"
+    return "output.wav" # return audio
 
 def caption_my_image(pil_image):
 
     semantics = caption_image(images=pil_image)[0]['generated_text']
     audio = generate_audio(semantics)
-    return semantics,audio
+    return semantics,audio  # returns both text and audio output
 
 
 gr.close_all()