Update app.py

app.py

@@ -24,39 +24,31 @@ genre_classes = {
     9: "Rock"
 }
 def get_melspec_feature(X, target_sr, frame_size, frame_shift_len, n_mels):
-    melspec_feature = []
-    for audio in X:
-        audio_melspec = librosa.feature.melspectrogram(y=audio, sr=target_sr, n_fft=frame_size, hop_length=frame_shift_len)
-        audio_melspec = librosa.power_to_db(audio_melspec)
-        audio_melspec = audio_melspec.T
-        melspec_feature.append(audio_melspec)
-    return np.array(melspec_feature, dtype=np.float32)
-
-def process_data_for_conv2D(X, resize_shape=None):
-    X_conv2D = []
-    for sample in X:
-        sample = np.reshape(sample, newshape=(sample.shape[0], sample.shape[1], 1))
-        if resize_shape:
-            sample = resize(sample, output_shape=resize_shape)
-        X_conv2D.append(sample)
-    return np.array(X_conv2D, dtype=np.float32)
+    
+    audio_melspec = librosa.feature.melspectrogram(y=X, sr=target_sr, n_fft=frame_size, hop_length=frame_shift_len)
+    audio_melspec = librosa.power_to_db(audio_melspec)
+    audio_melspec = audio_melspec.T
+    print(audio_melspec.shape)
+    return np.array(audio_melspec, dtype=np.float32)
 
 
 def predict_genre(audio):
-    sr, audio = audio
-    # print(audio)
-    # audio = np.ndarray(audio)
-    audio = audio.astype(np.float32)
-    melspec = get_melspec_feature(audio, target_sr, frame_size, frame_shift_len, 128) 
-    melspec = process_data_for_conv2D(melspec)
+    # print(type(audio[1]))
+    print(audio)
+    start = random.randint(1, 15)
+    x, sr = librosa.load(audio, offset=start, duration=10.0)
+    # # print(audio)
+    # print(type(x))
+    melspec = get_melspec_feature(x, target_sr, frame_size, frame_shift_len, 128)
+    melspec = np.reshape(melspec, (-1, 431, 128, 1))
     prediction = model.predict(melspec)[0]
-    return {genre_classes[i]: float(prediction[i]) for i in range(5)}
+    return {genre_classes[i]: float(prediction[i]) for i in range(10)}
 
 
 iface = gr.Interface(
     predict_genre, 
-    inputs=gr.inputs.Audio(type="numpy", label="Upload Music file"),
-    outputs=gr.outputs.Label(num_top_classes=5),
+    inputs=gr.inputs.Audio(type="filepath", label="Upload Music file"),
+    outputs=gr.outputs.Label(num_top_classes=10),
     title="Music Genre Classifier",
     live=True
 )