Update app.py

app.py

@@ -5,7 +5,7 @@ from moviepy.editor import *
 from share_btn import community_icon_html, loading_icon_html, share_js
 
 token = os.environ.get('HF_TOKEN')
-caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
+caption = gr.Blocks.load(name="spaces/laion/CoCa")
 audio_gen = gr.Blocks.load(name="spaces/fffiloni/audioldm-text-to-audio-generation-clone", api_key=token)
 
 ph_message="If you're not happy with sound result, you can manually describe the scene depicted in your image :)"
@@ -16,8 +16,8 @@ def input_changes(input_img):
         return manual_cap.update(value="",placeholder=ph_message), caption_output.update(value=None), sound_output.update(value=None)
     else:
         cap = caption(input_img, fn_index=0)
-        print("gpt2 caption: '" + cap + "' • ")
-        ph_update = "gpt2 caption: '" + cap + "' • "
+        print("CoCa caption: '" + cap + "' • ")
+        ph_update = "CoCa caption: '" + cap + "' • "
         
         return manual_cap.update(value="",placeholder=f"{ph_update}{ph_message}"), caption_output.update(value=cap), sound_output.update(value=None)
  
@@ -27,8 +27,8 @@ def infer(image_input, manual_caption, duration_in, seed, caption_output):
     if manual_caption == "":
         cap = caption_output
         #cap = caption(image_input, fn_index=0)
-        #print("gpt2 caption: '" + cap + "' • ")
-        #ph_update = "gpt2 caption: '" + cap + "' • "
+        #print("CoCa caption: '" + cap + "' • ")
+        #ph_update = "CoCa caption: '" + cap + "' • "
     else:
         cap = manual_caption
         print("manual caption: " + cap)
@@ -54,7 +54,7 @@ title = """
         </h1>
         </div>
         <p style="margin-bottom: 10px; font-size: 94%">
-        Convert an image to a corresponding sound effect generated through GPT2 Image Captioning & AudioLDM
+        Convert an image to a corresponding sound effect generated through CoCa Image Captioning & AudioLDM
         </p>
     </div>
 """