Update app.py

app.py

@@ -3,6 +3,7 @@ import langcodes
 from transformers import pipeline, VitsModel, AutoTokenizer, set_seed
 from huggingface_hub import InferenceClient
 from langdetect import detect, DetectorFactory
+import torch
 import uuid
 import scipy.io.wavfile as wav
 
@@ -144,6 +145,15 @@ with playground:
                     # generate_audio_button = gr.Button(value="Generate Audio", variant="primary")
                     audio_output = gr.Audio(type="filepath", label="Generated Speech")
                     ITT_Clear_button = gr.ClearButton(components=[img, generated_textbox], value="Clear")
+                    
+                    gr.Examples(
+                        examples=[
+                            ["lion-dog-costume.jpg"], 
+                            ["dog-halloween.jpeg"]
+                        ], 
+                        inputs=[img], 
+                        outputs=[generated_textbox, audio_output], 
+                        run_on_click=True, cache_examples=True, fn=launch_image_pipe)
                         
             ITT_button.click(launch_image_pipe, inputs=[img], outputs=[generated_textbox, audio_output])
             # generate_audio_button.click(generate_audio, inputs=[generated_textbox], outputs=[audio_output])