Update app.py

app.py

@@ -9,7 +9,15 @@ import tempfile
 learn = load_learner('model.pkl')
 labels = learn.dls.vocab
 
-def audio_to_spectrogram(audio_file, sr): 
+
+def record_audio(duration=3, sr=44100, channels=1):
+    print("Recording...")
+    audio = sd.rec(int(duration * sr), samplerate=sr, channels=channels, dtype='float32')
+    sd.wait()
+    print("Recording stopped.")
+    return audio, sr
+    
+def audio_to_spectrogram(audio_file,): 
     if audio_file.endswith('.mp3'):
         with tempfile.NamedTemporaryFile(suffix='.wav') as temp_wav:
             audio = AudioSegment.from_mp3(audio_file)
@@ -29,25 +37,6 @@ def audio_to_spectrogram(audio_file, sr):
     plt.close()
     return spectrogram_file
 
-def record_audio(duration=3, sr=44100, channels=1):
-    print("Recording...")
-    audio = sd.rec(int(duration * sr), samplerate=sr, channels=channels, dtype='float32')
-    sd.wait()
-    print("Recording stopped.")
-    return audio, sr
-
-def audio_to_spectrogram(audio, sr): 
-    S = librosa.feature.melspectrogram(y=audio[:, 0], sr=sr, n_mels=128, fmax=8000)
-    S_dB = librosa.power_to_db(S, ref=np.max)
-    fig, ax = plt.subplots()
-    img = librosa.display.specshow(S_dB, x_axis='time', y_axis='mel', sr=sr, fmax=8000, ax=ax)
-    fig.colorbar(img, ax=ax, format='%+2.0f dB')
-    ax.set(title='Mel-frequency spectrogram')
-    spectrogram_file = "spectrogram.png"
-    plt.savefig(spectrogram_file)
-    plt.close()
-    return spectrogram_file
-
 def predict(audio):
     spectrogram_file = audio_to_spectrogram(audio)
     img = PILImage.create(spectrogram_file)