Change inputs to list

app.py

@@ -118,7 +118,7 @@ with demo:
             midi_audio = gr.Audio()
         
         btn.click(inference,
-                  inputs="final_audio.wav",
+                  inputs=["final_audio.wav"],
                   outputs=[midi_file, midi_audio])
         
         gr.Markdown(article)

utils.py

@@ -1,14 +1,13 @@
 
-import tempfile
 import collections
 
-import note_seq
-
 import pandas as pd
+import plotly.express as px
 import matplotlib.pyplot as plt
 from matplotlib.patches import Rectangle
 from PIL import Image
 
+import note_seq
 class AudioIOReadError(BaseException):  # pylint:disable=g-bad-exception-name
   pass
 
@@ -31,8 +30,15 @@ def dataframe_to_pianoroll_img(df):
     fig = plt.figure(figsize=(8, 5))
     ax = fig.add_subplot(111)
     ax.scatter(df.start_time, df.pitch, c="white")
+    n_colors = len(df.instrument.unique())
+    colorscale = px.colors.sample_colorscale("viridis", [n/(n_colors -1) for n in range(n_colors)])
+    colordict = {f:colorscale[i] for i, f in enumerate(df.instrument.unique())}
     for _, row in df.iterrows():
-        ax.add_patch(Rectangle((row["start_time"], row["pitch"]-0.4), row["duration"], 0.4, color="black"))
+        ax.add_patch(Rectangle((row["start_time"],
+                                row["pitch"]-0.4),
+                               row["duration"],
+                               0.4,
+                               color=colordict[row["instrument"]]))
     plt.xlabel('time (sec.)', fontsize=18)
     plt.ylabel('pitch (MIDI)', fontsize=16)
     return fig