Update app.py

app.py

@@ -116,9 +116,9 @@ mic_translate = gr.Interface(
 )
 
 # File translation using uploaded files as input
-file_translate = gr.Interface(
+audio_translate = gr.Interface(
     fn=speech_to_speech_translation,
-    inputs=gr.Audio(source="upload", type="filepath"),
+    inputs=[[gr.Audio(source="microphone", type="filepath")], [gr.Audio(source="upload", type="filepath")]],
     outputs=gr.Audio(label="Generated Speech", type="numpy"),
     examples=[["./english.wav"], ["./chinese.wav"]],
     title=title,
@@ -134,7 +134,65 @@ text_translate = gr.Interface(
     description=description
 )
 
-with gr.Blocks(css=css) as image:
+# Inputs for Image Generation
+prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+
+negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+                visible=False,
+            )
+
+seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
+
+randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+
+width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=512,
+                )
+                
+height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=512,
+                )
+
+guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=10.0,
+                    step=0.1,
+                    value=0.0,
+                )
+                
+num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=12,
+                    step=1,
+                    value=2,
+                )
+
+'''with gr.Blocks(css=css) as image:
     
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""
@@ -221,16 +279,23 @@ with gr.Blocks(css=css) as image:
         inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
         outputs = [result]
     )
+'''
 
 # Text to Image interface
 image_generation = gr.Interface(
     fn=infer,
     inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-    outputs=[result]
+    outputs=[result],
+    examples=gr.Examples(
+            examples = examples,
+            inputs = [prompt]
+        ),
+    title=title,
+    description=description,
 )
 
 # Showcase the demo using different tabs of the different features
 with demo:
-    gr.TabbedInterface([mic_translate, file_translate, text_translate, image_generation], ["Microphone", "Audio File", "Text to Speech", "Text to Image"])
+    gr.TabbedInterface([audio_translate, file_translate, text_translate, image_generation], ["Speech to Text", "Audio File", "Text to Speech", "Text to Image"])
 
 demo.launch()