File size: 1,564 Bytes
6fa9813 |
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 |
import gradio as gr
from fastai.vision.all import *
import librosa
import numpy as np
import matplotlib.pyplot as plt
from pydub import AudioSegment
import tempfile
learn = load_learner('model.pkl')
labels = learn.dls.vocab
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)
audio.export(temp_wav.name, format='wav')
y, sr = librosa.load(temp_wav.name, sr=None)
else:
y, sr = librosa.load(audio_file, sr=None)
S = librosa.feature.melspectrogram(y=y, 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)
img = img.resize((512, 512))
pred, pred_idx, probs = learn.predict(img)
return {labels[i]: float(probs[i]) for i in range(len(labels))}
examples = ['example_audio.mp3']
gr.Interface(
fn=predict,
inputs=gr.inputs.Audio(source="upload", type="filepath", label="Upload audio (WAV or MP3)"),
outputs=gr.components.Label(num_top_classes=3),
examples=examples,
).launch() |