Update app.py

app.py

@@ -15,6 +15,7 @@ from typing import Union
 from diffusers.utils.torch_utils import randn_tensor
 from tqdm import tqdm
 from TangoFlux import TangoFluxInference
+import torchaudio
 
 
 
@@ -44,7 +45,7 @@ Generate audio using Tango2 by providing a text prompt. Tango2 was built from Ta
 """
 # Gradio input and output components
 input_text = gr.Textbox(lines=2, label="Prompt")
-output_format = gr.Radio(label = "Output format", info = "The file you can dowload", choices = ["mp3", "wav"], value = "wav")
+#output_format = gr.Radio(label = "Output format", info = "The file you can dowload", choices =  "wav"], value = "wav")
 output_audio = gr.Audio(label="Generated Audio", type="filepath")
 denoising_steps = gr.Slider(minimum=10, maximum=100, value=25, step=5, label="Steps", interactive=True)
 guidance_scale = gr.Slider(minimum=1, maximum=10, value=3, step=0.1, label="Guidance Scale", interactive=True)
@@ -53,7 +54,7 @@ duration_scale = gr.Slider(minimum=1, maximum=30, value=10, step=1, label="Durat
 # Gradio interface
 gr_interface = gr.Interface(
     fn=gradio_generate,
-    inputs=[input_text, output_format, denoising_steps, guidance_scale,duration_scale],
+    inputs=[input_text, denoising_steps, guidance_scale,duration_scale],
     outputs=[output_audio],
     title="TangoFlux: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization",
     description=description_text,