up

app.py

@@ -38,7 +38,7 @@ description = """
 <a style="display:inline-block" href='https://github.com/charactr-platform/vocos'><img src='https://img.shields.io/github/stars/charactr-platform/vocos?style=social' /></a>
 <a style="display:inline-block; margin-left: 1em" href="https://huggingface.co/spaces/hf-audio/vocos-bark?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space%20to%20skip%20the%20queue-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
 </div>
-Bark is a universal text-to-audio model created by [Suno](www.suno.ai), with code publicly available [here](https://github.com/suno-ai/bark). \
+Bark is a universal text-to-audio model created by Suno. \
 Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. \
 In this demo, we leverage charactr.ai's Vocos model to create high quality audio from bark. \
 """
@@ -79,18 +79,20 @@ def generate_audio(text, voice_preset = None, lag = 0):
 with gr.Blocks() as demo_blocks:
     gr.Markdown(title)
     gr.Markdown(description)
-    with gr.Column():
-        inp_text = gr.Textbox(label="Input Text", info="What would you like bark to synthesise?")
-        spk = gr.Dropdown(
-                speaker_embeddings,
-                value=None, 
-                label="Acoustic Prompt", 
-                info="Default: Unconditional Generation"
-                )
-        btn = gr.Button("Synthesise speech!")
+    with gr.Row():
+        with gr.Column():
+            inp_text = gr.Textbox(label="Input Text", info="What would you like bark to synthesise?")
+            spk = gr.Dropdown(
+                    speaker_embeddings,
+                    value=None, 
+                    label="Acoustic Prompt", 
+                    info="Default: Unconditional Generation"
+                    )
+            btn = gr.Button("Generate Audio!")
     
-    with gr.Column():
-        out_audio_vocos = gr.Audio(type="numpy", autoplay=False, label="Generated Audio", show_label=True)
-        btn.click(generate_audio, [inp_text, spk], [out_audio_vocos])
+        with gr.Column():
+            out_audio_vocos = gr.Audio(type="numpy", autoplay=False, label="Generated Audio", show_label=True)
+    
+    btn.click(generate_audio, [inp_text, spk], [out_audio_vocos])
 
 demo_blocks.queue().launch(debug=True)