New interface

app.py

@@ -84,17 +84,19 @@ def gradio_generate(prompt, steps, guidance):
     output_wave = tango.generate(prompt, steps, guidance)
     return gr.make_waveform((16000, output_wave))
 
-description_text = """
+# Gradio interface
+with gr.Blocks() as interface:
+    gr.Markdown("""
         <p style="text-align: center;">
         <b><big><big><big>Text-to-Audio</big></big></big></b>
         <br/>Generates an audio file, freely, without account, without watermark, that you can download.
         </p>
         <br/>
         <br/>
-        🚀 Powered by <i>Tango 2</i> AI.
+        ✨ Powered by <i>Tango 2</i> AI.
         <br/>
         <ul>
-        <li>If you need to generate <b>music</b>, I recommend you to use <i>MusicGen</i>,</li>
+        <li>If you need to generate <b>music</b>, I recommend to use <i>MusicGen</i>,</li>
         </ul>
         <br/>
         🐌 Slow process... Your computer must <b><u>not</u></b> enter into standby mode.<br/>You can duplicate this space on a free account, it works on CPU.<br/>
@@ -102,48 +104,41 @@ description_text = """
         <br/>
         ⚖️ You can use, modify and share the generated sounds but not for commercial uses.
         """
-# Gradio input and output components
-input_text = gr.Textbox(label = "Prompt", value = "Snort of a horse", lines = 2, autofocus = True)
-denoising_steps = gr.Slider(label = "Steps", minimum = 100, maximum = 200, value = 100, step = 1, interactive = True)
-guidance_scale = gr.Slider(label = "Guidance Scale", minimum = 1, maximum = 10, value = 3, step = 0.1, interactive = True)
+    )
+    input_text = gr.Textbox(label = "Prompt", value = "Snort of a horse", lines = 2, autofocus = True)
+    denoising_steps = gr.Slider(label = "Steps", minimum = 100, maximum = 200, value = 100, step = 1, interactive = True)
+    guidance_scale = gr.Slider(label = "Guidance Scale", minimum = 1, maximum = 10, value = 3, step = 0.1, interactive = True)
 
-output_audio = gr.Audio(label = "Generated Audio")
+    submit = gr.Button("Generate 🚀", variant = "primary")
 
-# Gradio interface
-gr_interface = gr.Interface(
-    fn = gradio_generate,
-    inputs = [input_text, denoising_steps, guidance_scale],
-    outputs = [output_audio],
-    title = "",
-    description = description_text,
-    allow_flagging = False,
-    examples = [
-        ["Quiet speech and then and airplane flying away"],
-        ["A bicycle peddling on dirt and gravel followed by a man speaking then laughing"],
-        ["Ducks quack and water splashes with some animal screeching in the background"],
-        ["Describe the sound of the ocean"],
-        ["A woman and a baby are having a conversation"],
-        ["A man speaks followed by a popping noise and laughter"],
-        ["A cup is filled from a faucet"],
-        ["An audience cheering and clapping"],
-        ["Rolling thunder with lightning strikes"],
-        ["A dog barking and a cat mewing and a racing car passes by"],
-        ["Gentle water stream, birds chirping and sudden gun shot"],
-        ["A man talking followed by a goat baaing then a metal gate sliding shut as ducks quack and wind blows into a microphone."],
-        ["A dog barking"],
-        ["A cat meowing"],
-        ["Wooden table tapping sound while water pouring"],
-        ["Applause from a crowd with distant clicking and a man speaking over a loudspeaker"],
-        ["two gunshots followed by birds flying away while chirping"],
-        ["Whistling with birds chirping"],
-        ["A person snoring"],
-        ["Motor vehicles are driving with loud engines and a person whistles"],
-        ["People cheering in a stadium while thunder and lightning strikes"],
-        ["A helicopter is in flight"],
-        ["A dog barking and a man talking and a racing car passes by"],
-    ],
-    cache_examples = "lazy", # Turn on to cache.
-)
+    output_audio = gr.Audio(label = "Generated Audio")
 
-# Launch Gradio app
-gr_interface.queue(10).launch()
+    submit.click(fn = gradio_generate, inputs = [
+        input_text,
+        denoising_steps,
+        guidance_scale
+    ], outputs = [
+        output_audio
+    ], scroll_to_output = True)
+
+    gr.Examples(
+        fn = gradio_generate,
+	    inputs = [
+            input_text,
+            denoising_steps,
+            guidance_scale
+        ],
+	    outputs = [
+            output_audio
+        ],
+        examples = [
+                ["A hammer is hitting a wooden surface", 100, 3],
+                ["Peaceful and calming ambient music with singing bowl and other instruments.", 100, 3],
+                ["A man is speaking in a small room.", 100, 3],
+                ["A female is speaking followed by footstep sound", 100, 3],
+                ["Wooden table tapping sound followed by water pouring sound.", 100, 3],
+            ],
+        cache_examples = False,
+    )
+        
+    interface.queue(10).launch()