Update app.py

app.py

@@ -1,8 +1,13 @@
 from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
 from transformers import pipeline
-from PIL import Image, ImageDraw, ImageFont
+from PIL import Image
 import gradio as gr
+import torch
 
+#this converts text to speech
+fastspeech = gr.Interface.load("huggingface/facebook/fastspeech2-en-ljspeech")
+
+#this function detects the objects in the room
 def object_classify(img1,img2):
 
   feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b2-finetuned-ade-512-512")
@@ -18,6 +23,9 @@ def object_classify(img1,img2):
   objects_1=[]
   objects_2=[]
   
+  #this is will read by the fastspeech
+  tts_words=['The missing items are']
+  
   #gets the label from each dictionary
   for i in dict_obj1:
     objects_1.append(i['label'])
@@ -27,16 +35,28 @@ def object_classify(img1,img2):
    
   #gets the uncommon elements from the 2 lists
   missing_objects= list(set(objects_1)-set(objects_2))
-  #missing_objects=*missing_objects, sep = ", "
-  return missing_objects
+  
+  if len(missing_objects)==0:
+    tts_words.append('None')
+  elif len(missing_objects)==1:
+    tts_words[0]='The missing item is'
+    tts_words.extend(missing_objects)
+  else:
+    tts_words.extend(missing_objects)
+    
+  gonna_process=' '.join(tts_words)
+ 
+
+  return missing_objects, fastspeech(gonna_process)
  
   
-TITLE = 'Missing Items'
+TITLE = 'Missing Items using Nvidia Segformer'
 DESCRIPTION = 'Input two indoor pictures. First image being the original and second is one with the missing item/s'
 EXAMPLES = [['Bedroom_1.jpg'],['Bedroom_2.jpg']]
 
 INPUTS=[gr.inputs.Image(type = 'pil', label='Original Image'),gr.inputs.Image(type = 'pil', label='Second Image')]
-OUTPUTS=gr.outputs.Textbox(label="Missing Item/s is/are: ")
+OUTPUTS=[gr.outputs.Textbox(label='Missing Item/s is/are'),gr.outputs.Audio(type="auto", label="Missing Items Audio")]
+
 
 interface=gr.Interface(object_classify,
                        INPUTS,