Spaces:
Runtime error
Runtime error
File size: 1,524 Bytes
c6798a7 2fbf82e 519b33d 2fbf82e d92f370 2fbf82e b8d1683 2fbf82e 40d3368 8a43324 2fbf82e 40d3368 e4373c4 40d3368 2fbf82e c6798a7 b3f2f5e 2fbf82e 40d3368 2fbf82e b3f2f5e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
import gradio as gr
import librosa
from tensorflow.keras.models import load_model
import numpy as np
import random
# load model
model = load_model("BBNN_model.hdf5")
# basic variables for mel spectrogram
target_sr = 22050
frame_size = 1024
frame_shift_len = 512
n_mels = 128
genre_classes = {
0: "Blues",
1: "Classical",
2: "Country",
3: "Disco",
4: "Hiphop",
5: "Jazz",
6: "Metal",
7: "Pop",
8: "Reggae",
9: "Rock"
}
def get_melspec_feature(X, target_sr, frame_size, frame_shift_len, n_mels):
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):
# 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(10)}
iface = gr.Interface(
predict_genre,
inputs=gr.inputs.Audio(type="filepath", label="Upload Music file"),
outputs=gr.outputs.Label(num_top_classes=10),
title="Music Genre Classifier",
live=True
)
iface.launch()
|