Upload app.py

app.py

@@ -0,0 +1,38 @@
+from cProfile import label
+import gradio as gr
+from fastai.vision.all import *
+from fastai.vision.all import *
+import matplotlib.pyplot as plt
+from matplotlib.pyplot import specgram
+import librosa
+import numpy as np
+import librosa.display
+
+def is_cat(x): return x[0]=='c' 
+
+def audio_to_spectrogram(audio_file):
+    samples,sample_rate = librosa.load(audio_file)
+    fig = plt.figure(figsize=[0.72,0.72])
+    ax = fig.add_subplot(111)
+    ax.axes.get_xaxis().set_visible(False)
+    ax.axes.get_yaxis().set_visible(False)
+    ax.set_frame_on(False)
+    filename = Path(audio_file).name.replace('mp3','png')
+    S = librosa.feature.melspectrogram(y=samples,sr=sample_rate)
+    librosa.display.specshow(librosa.power_to_db(S,ref=np.max))
+    plt.savefig(filename,dpi=400,bbox_inches='tight',pad_inches=0)
+    plt.close('all')
+    return filename
+
+categories = ('Dog','Cat')
+def catvsdogsoundclassification(audio_file):
+    print('in the function')
+    filename = audio_to_spectrogram(audio_file)
+    learner = load_learner('model.pkl')
+    pred,pred_idx,probs = learner.predict(filename)
+    return dict(zip(categories,map(float,probs)))
+
+# audio_file = gr.inputs.Audio()
+labeel = gr.outputs.Label()
+intf = gr.Interface(fn=catvsdogsoundclassification,inputs=gr.Audio(),outputs=labeel)
+intf.launch(inline=False,debug=True)