up

app.py

@@ -31,6 +31,20 @@ SAMPLE_RATE = 24_000
 
 vocos = Vocos.from_pretrained("charactr/vocos-encodec-24khz").to(device)
 
+title = "# 🐶 Bark with Charactr.ai's <a href='https://github.com/charactr-platform/vocos'>Vocos</a></div>"
+
+description = """
+<div>
+<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 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. \
+The model output is not censored and the authors do not endorse the opinions in the generated content. \
+Use at your own risk.
+"""
+
 # import model
 if device == "cpu":
     bark = BarkModel.from_pretrained(HUB_PATH)
@@ -65,23 +79,19 @@ def generate_audio(text, voice_preset = None, lag = 0):
 
 # Gradio blocks demo    
 with gr.Blocks() as demo_blocks:
-    gr.Markdown("""<h1 align="center">🐶 Bark with Vocos</h1>""")
-    gr.HTML("""<h3 style="text-align:center;">📢 Vocos-enhanced TTS 🦾! </h3>""")
-    with gr.Group():
-        with gr.Row():
-            inp_text = gr.Textbox(label="What should Bark say?", info="Enter text here")
-        with gr.Row():
-            spk = gr.Dropdown(
+    gr.Markdown(title)
+    gr.Markdown(description)
+    with gr.column():
+        inp_text = gr.Textbox(label="What should Bark say?", info="Enter text here")
+        spk = gr.Dropdown(
                 speaker_embeddings,
                 value=None, 
                 label="Available voice presets", 
                 info="Default: No speaker embeddings"
                 )
-    
-    with gr.Row():
         btn = gr.Button("Synthesise speech!")
     
-    with gr.Row():
+    with gr.column():
         out_audio_vocos = gr.Audio(type="numpy", autoplay=False, label="Vocos enhanced speech", show_label=True)
         
         btn.click(generate_audio, [inp_text, spk], [out_audio_vocos])