Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from transformers import AutoProcessor, BarkModel
 import scipy
-from IPython.display import Audio
+import numpy as np
 
 # Load the processor and model
 processor = AutoProcessor.from_pretrained("suno/bark")
@@ -12,18 +12,23 @@ def generate_audio(text):
     voice_preset = "v2/en_speaker_6"
     inputs = processor(text, voice_preset=voice_preset)
     audio_array = model.generate(**inputs)
+    # Move the tensor to CPU and convert to numpy array
     audio_array = audio_array.cpu().numpy().squeeze()
     sample_rate = model.generation_config.sample_rate
-    
-    # Write the output to a .wav file
-    scipy.io.wavfile.write("bark_out.wav", rate=sample_rate, data=audio_array)
-    return "bark_out.wav"
 
-# Create the Gradio interface
+    # Saving the audio file temporarily
+    output_file = '/tmp/bark_out.wav'
+    scipy.io.wavfile.write(output_file, rate=sample_rate, data=audio_array)
+
+    # Return the path to the saved audio file
+    return output_file
+
+# Define the Gradio interface
 iface = gr.Interface(
     fn=generate_audio,
-    inputs=gr.inputs.Textbox(label="标入prompt(input)"),
-    outputs=gr.outputs.Audio(label="生成音频(button)", type="file"),
+    inputs="text",
+    outputs="audio",
+    examples=[["Hello, my dog is cute"]],
     allow_flagging="never"
 )