Update app.py

app.py

@@ -214,79 +214,102 @@ def toggle_audio_src(choice):
 
 
 def ui_full(launch_kwargs):
-    interface = gr.Interface(
-        fn=predict_full,
-        inputs=[
-            gr.Radio(["melody", "medium", "small", "large"], label="Model", default="melody"),
-            gr.Text(label="Input Text"),
-            gr.Audio(source="upload", type="numpy", label="File", interactive=True, elem_id="melody-input"),
-            gr.Slider(minimum=1, maximum=120, default=10, label="Duration", step=1),
-            gr.Number(label="Top-k", default=250),
-            gr.Number(label="Top-p", default=0),
-            gr.Number(label="Temperature", default=1.0),
-            gr.Number(label="Classifier Free Guidance", default=3.0),
-        ],
-        outputs=[
-           gr.Audio(type='filepath',label="Generated Music"), 
-           gr.Audio(type='filepath',label="Vocal Music"),
-           gr.Audio(type='filepath',label="base Music"), 
-           gr.Audio(type='filepath',label="drum Music"),
-           gr.Audio(type='filepath',label="other Music")
-            #gr.outputs.Audio(type='filepath')
-        ],
-        title="MusicGen",
-        description="This is your private demo for MusicGen, a simple and controllable model for music generation.",
-        allow_flagging="never",
-        layout="vertical",
-        **launch_kwargs
-    )
-
-    interface.launch()
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        '--listen',
-        type=str,
-        default='0.0.0.0' if 'SPACE_ID' in os.environ else '127.0.0.1',
-        help='IP to listen on for connections to Gradio',
-    )
-    parser.add_argument(
-        '--username', type=str, default='', help='Username for authentication'
-    )
-    parser.add_argument(
-        '--password', type=str, default='', help='Password for authentication'
-    )
-    parser.add_argument(
-        '--server_port',
-        type=int,
-        default=0,
-        help='Port to run the server listener on',
-    )
-    parser.add_argument(
-        '--inbrowser', action='store_true', help='Open in browser'
-    )
-    parser.add_argument(
-        '--share', action='store_true', help='Share the gradio UI'
-    )
-
-    args = parser.parse_args()
-
-    launch_kwargs = {}
-    launch_kwargs['server_name'] = args.listen
-
-    if args.username and args.password:
-        launch_kwargs['auth'] = (args.username, args.password)
-    if args.server_port:
-        launch_kwargs['server_port'] = args.server_port
-    if args.inbrowser:
-        launch_kwargs['inbrowser'] = args.inbrowser
-    if args.share:
-        launch_kwargs['share'] = args.share
+    with gr.Blocks() as interface:
+        gr.Markdown(
+            """
+            # MusicGen
+            This is your private demo for [MusicGen](https://github.com/facebookresearch/audiocraft),
+            a simple and controllable model for music generation
+            presented at: ["Simple and Controllable Music Generation"](https://huggingface.co/papers/2306.05284)
+            """
+        )
+        with gr.Row():
+            with gr.Column():
+                with gr.Row():
+                    text = gr.Text(label="Input Text", interactive=True)
+                    with gr.Column():
+                        radio = gr.Radio(["file", "mic"], value="file",
+                                         label="Condition on a melody (optional) File or Mic")
+                        melody = gr.Audio(source="upload", type="numpy", label="File",
+                                          interactive=True, elem_id="melody-input")
+                with gr.Row():
+                    submit = gr.Button("Submit")
+                    # Adapted from https://github.com/rkfg/audiocraft/blob/long/app.py, MIT license.
+                with gr.Row():
+                    model = gr.Radio(["melody", "medium", "small", "large"],
+                                     label="Model", value="melody", interactive=True)
+                with gr.Row():
+                    duration = gr.Slider(minimum=1, maximum=120, value=10, label="Duration", interactive=True)
+                with gr.Row():
+                    topk = gr.Number(label="Top-k", value=250, interactive=True)
+                    topp = gr.Number(label="Top-p", value=0, interactive=True)
+                    temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
+                    cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
+            with gr.Column():
+                output = [gr.Audio(label="Generated Music"),gr.Audio(label="Generated Music"),gr.Audio(label="Generated Music"),gr.Audio(label="Generated Music"),gr.Audio(label="Generated Music")]
+        submit.click(predict_full,
+                     inputs=[model, text, melody, duration, topk, topp, temperature, cfg_coef],
+                     outputs=[output])
+        radio.change(toggle_audio_src, radio, [melody], queue=False, show_progress=False)
+        gr.Examples(
+            fn=predict_full,
+            examples=[
+                [
+                    "An 80s driving pop song with heavy drums and synth pads in the background",
+                    "./assets/bach.mp3",
+                    "melody"
+                ],
+                [
+                    "A cheerful country song with acoustic guitars",
+                    "./assets/bolero_ravel.mp3",
+                    "melody"
+                ],
+                [
+                    "90s rock song with electric guitar and heavy drums",
+                    None,
+                    "medium"
+                ],
+                [
+                    "a light and cheerly EDM track, with syncopated drums, aery pads, and strong emotions",
+                    "./assets/bach.mp3",
+                    "melody"
+                ],
+                [
+                    "lofi slow bpm electro chill with organic samples",
+                    None,
+                    "medium",
+                ],
+            ],
+            inputs=[text, melody, model],
+            outputs=[output]
+        )
+        gr.Markdown(
+            """
+            ### More details
+            The model will generate a short music extract based on the description you provided.
+            The model can generate up to 30 seconds of audio in one pass. It is now possible
+            to extend the generation by feeding back the end of the previous chunk of audio.
+            This can take a long time, and the model might lose consistency. The model might also
+            decide at arbitrary positions that the song ends.
+            **WARNING:** Choosing long durations will take a long time to generate (2min might take ~10min).
+            An overlap of 12 seconds is kept with the previously generated chunk, and 18 "new" seconds
+            are generated each time.
+            We present 4 model variations:
+            1. Melody -- a music generation model capable of generating music condition
+                on text and melody inputs. **Note**, you can also use text only.
+            2. Small -- a 300M transformer decoder conditioned on text only.
+            3. Medium -- a 1.5B transformer decoder conditioned on text only.
+            4. Large -- a 3.3B transformer decoder conditioned on text only (might OOM for the longest sequences.)
+            When using `melody`, ou can optionaly provide a reference audio from
+            which a broad melody will be extracted. The model will then try to follow both
+            the description and melody provided.
+            You can also use your own GPU or a Google Colab by following the instructions on our repo.
+            See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft)
+            for more details.
+            """
+        )
 
-    # Show the interface
-    ui_full(launch_kwargs)
+        interface.queue().launch(**launch_kwargs)
 
 
 def ui_batched(launch_kwargs):