Update app.py

app.py

@@ -138,22 +138,24 @@ def ui_full(launch_kwargs):
     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="Текст пример (bass drum cyberpunk)", interactive=True)
+                    text = gr.Text(label="Input Text", interactive=True)
                     melody = gr.Audio(source="upload", type="numpy", label="Melody Condition (optional)", interactive=True)
                 with gr.Row():
-                    submit = gr.Button("Создать")
-                
-                    _ = gr.Button("Прервать").click(fn=interrupt, queue=False)
+                    submit = gr.Button("Submit")
+                    # Adapted from https://github.com/rkfg/audiocraft/blob/long/app.py, MIT license.
+                    _ = gr.Button("Interrupt").click(fn=interrupt, queue=False)
                 with gr.Row():
-                    model = gr.Radio(["melody", "medium", "small", "large"], label="Тип трека", value="melody", interactive=True)
+                    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="Время трека(seconds)", interactive=True)
+                    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)
@@ -162,10 +164,58 @@ def ui_full(launch_kwargs):
             with gr.Column():
                 output = gr.Video(label="Generated Music")
         submit.click(predict_full, inputs=[model, text, melody, duration, topk, topp, temperature, cfg_coef], outputs=[output])
-   
+        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.
             """
         )
 
@@ -176,13 +226,19 @@ def ui_batched(launch_kwargs):
     with gr.Blocks() as demo:
         gr.Markdown(
             """
-           
+            # MusicGen
+            This is the 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).
+            <br/>
+            <a href="https://huggingface.co/spaces/facebook/MusicGen?duplicate=true" style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank">
+            <img style="margin-bottom: 0em;display: inline;margin-top: -.25em;" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
+            for longer sequences, more control and no queue.</p>
             """
         )
         with gr.Row():
             with gr.Column():
                 with gr.Row():
-                   text = gr.Text(label="Describe your music", lines=2, interactive=True)
+                    text = gr.Text(label="Describe your music", lines=2, interactive=True)
                     melody = gr.Audio(source="upload", type="numpy", label="Condition on a melody (optional)", interactive=True)
                 with gr.Row():
                     submit = gr.Button("Generate")
@@ -218,14 +274,11 @@ def ui_batched(launch_kwargs):
         )
         gr.Markdown("""
         ### More details
-
         The model will generate 12 seconds of audio based on the description you provided.
         You 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.
         All samples are generated with the `melody` model.
-
         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.
         """)
@@ -278,4 +331,4 @@ if __name__ == "__main__":
     if IS_BATCHED:
         ui_batched(launch_kwargs)
     else:
-        ui_full(launch_kwargs) 
+        ui_full(launch_kwargs)