fix

app.py

@@ -129,7 +129,8 @@ with gr.Blocks() as demo:
         """
         ### More details
 
-        By typing a description of the music you want and an optional audio used for melody conditioning,
+        The model will generate a short music extract based on the description you provided.
+        You can generate up to 30 seconds of audio.
 
         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.
@@ -137,8 +138,12 @@ with gr.Blocks() as demo:
         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 the optional melody conditioning wav is provided, the model will extract
-        a broad melody and try to follow it in the generated samples.
+        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.
         """
     )
 

app_batched.py

@@ -73,7 +73,7 @@ with gr.Blocks() as demo:
         <br/>
         <a href="https://huggingface.co/spaces/musicgen/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>
+        for longer sequences, more control and no queue.</p>
         """
     )
     with gr.Row():
@@ -115,8 +115,11 @@ with gr.Blocks() as demo:
     )
     gr.Markdown("""
     ### More details
-    By typing a description of the music you want and an optional audio used for melody conditioning,
-    the model will extract the broad melody from the uploaded wav if provided and generate a 12s extract with the `melody` model.
+
+    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.