Update app.py

app.py

@@ -4,7 +4,7 @@ import numpy as np
 import torch
 from infer_rvc_python import BaseLoader
 
-# Initialize the audio transformation model, but don't configure it yet
+# Initialize the audio transformation model
 converter = BaseLoader(only_cpu=False, hubert_path=None, rmvpe_path=None)
 
 # Path to the models directory
@@ -27,12 +27,12 @@ def configure_model(file_model, file_index):
         consonant_breath_protection=0.5,
         resample_sr=44100
     )
-    return "Model configured successfully.", gr.update(visible=True)
+    return "Model configured successfully."
 
 # Function to process each audio chunk
-def transform_audio_chunk(audio, instream):
+def transform_audio_chunk(audio):
     if audio is None:
-        return None, instream
+        return None
     
     audio_data = torch.tensor(audio[1], dtype=torch.float32).unsqueeze(0)  # Prepare audio for processing
     with torch.no_grad():
@@ -41,12 +41,7 @@ def transform_audio_chunk(audio, instream):
             tag="live_transform",
         )
 
-    # Update the stream by concatenating the new transformed audio chunk
-    if instream is None:
-        return (audio[0], transformed_audio.squeeze(0).numpy()), (audio[0], transformed_audio.squeeze(0).numpy())
-    else:
-        new_stream = np.concatenate((instream[1], transformed_audio.squeeze(0).numpy()))
-        return (audio[0], new_stream), (audio[0], new_stream)
+    return audio[0], transformed_audio.squeeze(0).numpy()
 
 # Gradio interface setup
 with gr.Blocks() as demo:
@@ -59,18 +54,16 @@ with gr.Blocks() as demo:
     index_file = gr.Dropdown(choices=index_files, label="Select Index File")
     configure_button = gr.Button("Configure Model")
     
-    # Audio input component with streaming enabled, initially hidden
-    inp = gr.Audio(sources="microphone", streaming=True, type="numpy", visible=False)
+    # Audio input component with streaming enabled
+    inp = gr.Audio(sources="microphone", streaming=True, type="numpy")
     # Audio output component to play back the transformed audio
-    out = gr.Audio(streaming=True)
-    # State to manage the ongoing audio stream
-    stream = gr.State()
-
+    out = gr.Audio()
+    
     # Link the input to the processing function and output
-    inp.stream(transform_audio_chunk, [inp, stream], [out, stream])
+    inp.stream(transform_audio_chunk, inputs=[inp], outputs=[out])
 
     # Link the model configuration button to the configure_model function
-    configure_button.click(configure_model, inputs=[model_file, index_file], outputs=[inp])
+    configure_button.click(configure_model, inputs=[model_file, index_file], outputs=[])
 
 if __name__ == "__main__":
     demo.launch()