Update app.py

app.py

@@ -8,6 +8,16 @@ from huggingface_hub import snapshot_download
 def get_source_image(image):   
         return image
 
+def preprocess_audio(audio):
+    """Handle audio input - extract filepath if it's a tuple"""
+    if audio is None:
+        return None
+    if isinstance(audio, tuple):
+        # If it's a tuple (sample_rate, data), return None or handle differently
+        # For file upload, we need the actual file path
+        return audio[1] if len(audio) > 1 else audio[0]
+    return audio
+
 try:
     import webui  # in webui
     in_webui = True
@@ -50,12 +60,12 @@ def sadtalker_demo():
         <br/><b>Alternatively, try our GitHub <a href=https://github.com/Winfredy/SadTalker> code </a> on your own GPU. </b> <a style='display:inline-block' href="https://github.com/Winfredy/SadTalker"><img src="https://img.shields.io/github/stars/Winfredy/SadTalker?style=social"/></a> \
         """)
         
-        with gr.Row(): #.style(equal_height=False):
+        with gr.Row():
             with gr.Column(variant='panel'):
                 with gr.Tabs(elem_id="sadtalker_source_image"):
                     with gr.TabItem('Source image'):
                         with gr.Row():
-                            source_image = gr.Image(label="Source image", sources=["upload"], type="filepath", elem_id="img2img_image") # .style(width=512)
+                            source_image = gr.Image(label="Source image", source="upload", type="filepath", elem_id="img2img_image")
 
 
                 with gr.Tabs(elem_id="sadtalker_driven_audio"):
@@ -63,22 +73,22 @@ def sadtalker_demo():
                         gr.Markdown("Possible driving combinations: <br> 1. Audio only 2. Audio/IDLE Mode + Ref Video(pose, blink, pose+blink) 3. IDLE Mode only 4. Ref Video only (all) ")
 
                         with gr.Row():
-                            driven_audio = gr.Audio(label="Input audio", sources=["upload"])
-                            driven_audio_no = gr.Audio(label="Use IDLE mode, no audio is required", sources=["upload"], visible=False)
+                            driven_audio = gr.Audio(label="Input audio", source="upload", type="filepath", format="wav")
+                            driven_audio_no = gr.Audio(label="Use IDLE mode, no audio is required", source="upload", type="filepath", format="wav", visible=False)
 
                             with gr.Column():
                                 use_idle_mode = gr.Checkbox(label="Use Idle Animation")
                                 length_of_audio = gr.Number(value=5, label="The length(seconds) of the generated video.")
-                                use_idle_mode.change(toggle_audio_file, inputs=use_idle_mode, outputs=[driven_audio, driven_audio_no]) # todo
+                                use_idle_mode.change(toggle_audio_file, inputs=use_idle_mode, outputs=[driven_audio, driven_audio_no])
 
                         with gr.Row():
-                            ref_video = gr.Video(label="Reference Video", sources=["upload"], elem_id="vidref") # .style(width=512)
+                            ref_video = gr.Video(label="Reference Video", source="upload", type="filepath", elem_id="vidref")
 
                             with gr.Column():
                                 use_ref_video = gr.Checkbox(label="Use Reference Video")
                                 ref_info = gr.Radio(['pose', 'blink','pose+blink', 'all'], value='pose', label='Reference Video',info="How to borrow from reference Video?((fully transfer, aka, video driving mode))")
 
-                            ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video]) # todo
+                            ref_video.change(ref_video_fn, inputs=ref_video, outputs=[use_ref_video])
 
 
             with gr.Column(variant='panel'): 
@@ -86,15 +96,13 @@ def sadtalker_demo():
                     with gr.TabItem('Settings'):
                         gr.Markdown("need help? please visit our [[best practice page](https://github.com/OpenTalker/SadTalker/blob/main/docs/best_practice.md)] for more detials")
                         with gr.Column(variant='panel'):
-                            # width = gr.Slider(minimum=64, elem_id="img2img_width", maximum=2048, step=8, label="Manually Crop Width", value=512) # img2img_width
-                            # height = gr.Slider(minimum=64, elem_id="img2img_height", maximum=2048, step=8, label="Manually Crop Height", value=512) # img2img_width
                             with gr.Row():
-                                pose_style = gr.Slider(minimum=0, maximum=45, step=1, label="Pose style", value=0) #
-                                exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1) # 
+                                pose_style = gr.Slider(minimum=0, maximum=45, step=1, label="Pose style", value=0)
+                                exp_weight = gr.Slider(minimum=0, maximum=3, step=0.1, label="expression scale", value=1)
                                 blink_every = gr.Checkbox(label="use eye blink", value=True)
 
                             with gr.Row():
-                                size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?") # 
+                                size_of_image = gr.Radio([256, 512], value=256, label='face model resolution', info="use 256/512 model?")
                                 preprocess_type = gr.Radio(['crop', 'resize','full', 'extcrop', 'extfull'], value='crop', label='preprocess', info="How to handle input image?")
                             
                             with gr.Row():
@@ -108,7 +116,7 @@ def sadtalker_demo():
                             submit = gr.Button('Generate', elem_id="sadtalker_generate", variant='primary')
                             
                 with gr.Tabs(elem_id="sadtalker_genearted"):
-                        gen_video = gr.Video(label="Generated video", format="mp4", scale=1) # .style(width=256)
+                        gen_video = gr.Video(label="Generated video", format="mp4")
 
         
 
@@ -209,7 +217,7 @@ def sadtalker_demo():
                             enhancer], 
                         outputs=[gen_video],
                         fn=sad_talker.test,
-                        cache_examples=False) # 
+                        cache_examples=os.getenv('SYSTEM') == 'spaces')
 
     return sadtalker_interface
  
@@ -217,5 +225,5 @@ def sadtalker_demo():
 if __name__ == "__main__":
 
     demo = sadtalker_demo()
-    demo.queue(max_size=10)
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.queue()
+    demo.launch()