1

app.py

@@ -77,6 +77,7 @@ def text2speech(text):
     return fastspeech(text)
     
 def engine(text_input):
+print(" ** Inside Enngine **")
     #Extract entities from text
     ner = gr.Interface.load("huggingface/flair/ner-english-ontonotes-large")
     entities = ner(text_input)
@@ -89,7 +90,8 @@ def engine(text_input):
     for ent in entities:
         img = gr.Interface.load("spaces/multimodalart/latentdiffusion")(ent[0],'50','256','256','1',10)[0] 
         img_list.append(img)
-     
+    
+    print('img_list size:',len(img_list))
     #Resizing all images produced to same size
     resize_img_list = resize(img_list)
      
@@ -98,6 +100,8 @@ def engine(text_input):
      
     #Calculate the desired frame per second based on given audio length and entities identified
     fps= entities_num / 19 #length of audio file   #13 / 19
+    fps = format(fps, '.5f')
+    print('fps is: ',fps)
      
     #Convert string of images into a video
     #clip = images_to_video(fps, resize_img_list)