Change to retrieve audio directly and not from file

app.py

@@ -56,10 +56,8 @@ def populate_metadata(link):
     return yt.thumbnail_url, yt.title, audio
 
 def inference(yt_audio):
-    with open(yt_audio, "rb") as fd:
-        contents = fd.read()
 
-    audio = upload_audio(contents,sample_rate=SAMPLE_RATE)
+    audio = upload_audio(yt_audio,sample_rate=SAMPLE_RATE)
 
     est_ns = inference_model(audio)
     
@@ -105,7 +103,7 @@ with demo:
             title = gr.Label(label="Video Title", placeholder="Title")
             img = gr.Image(label="Thumbnail")
         with gr.Row():
-            yt_audio = gr.Audio(type="filepath", label="First 10 seconds")
+            yt_audio = gr.Audio()
 
         link.change(fn=populate_metadata, inputs=link, outputs=[img, title, yt_audio])
         

utils.py

@@ -2,7 +2,7 @@
 import tempfile
 import collections
 
-import librosa
+import note_seq
 
 import pandas as pd
 import matplotlib.pyplot as plt
@@ -13,51 +13,7 @@ class AudioIOReadError(BaseException):  # pylint:disable=g-bad-exception-name
   pass
 
 def upload_audio(audio, sample_rate):
-  
-  return wav_data_to_samples_librosa(audio, sample_rate=sample_rate)
-  
-def wav_data_to_samples_librosa(audio_file, sample_rate):
-  """Loads an in-memory audio file with librosa.
-  Use this instead of wav_data_to_samples if the wav is 24-bit, as that's
-  incompatible with wav_data_to_samples internal scipy call.
-  Will copy to a local temp file before loading so that librosa can read a file
-  path. Librosa does not currently read in-memory files.
-  It will be treated as a .wav file.
-  Args:
-    audio_file: Wav file to load.
-    sample_rate: The number of samples per second at which the audio will be
-        returned. Resampling will be performed if necessary.
-  Returns:
-    A numpy array of audio samples, single-channel (mono) and sampled at the
-    specified rate, in float32 format.
-  Raises:
-    AudioIOReadException: If librosa is unable to load the audio data.
-  """
-  with tempfile.NamedTemporaryFile(suffix='.wav') as wav_input_file:
-    wav_input_file.write(audio_file)
-    # Before copying the file, flush any contents
-    wav_input_file.flush()
-    # And back the file position to top (not need for Copy but for certainty)
-    wav_input_file.seek(0)
-    return load_audio(wav_input_file.name, sample_rate)
-
-def load_audio(audio_filename, sample_rate, duration=10):
-  """Loads an audio file.
-  Args:
-    audio_filename: File path to load.
-    sample_rate: The number of samples per second at which the audio will be
-        returned. Resampling will be performed if necessary.
-  Returns:
-    A numpy array of audio samples, single-channel (mono) and sampled at the
-    specified rate, in float32 format.
-  Raises:
-    AudioIOReadError: If librosa is unable to load the audio data.
-  """
-  try:
-    y, unused_sr = librosa.load(audio_filename, sr=sample_rate, mono=True, duration=duration)
-  except Exception as e:  # pylint: disable=broad-except
-    raise AudioIOReadError(e)
-  return y
+  return note_seq.audio_io.wav_data_to_samples_librosa(audio, sample_rate=sample_rate)
 
 # Generate piano_roll
 def sequence_to_pandas_dataframe(sequence):