[UPD] app.py

app.py

@@ -1,17 +1,19 @@
 import streamlit as st
 import librosa
 import numpy as np
-import pickle
+import pandas as pd
 import IPython.display as ipd
 from sklearn.preprocessing import LabelEncoder
 from tensorflow.keras.models import load_model
 
 
-# le = LabelEncoder()
-
 model = load_model('model/audio_prediction_model')
 
 
+df = pd.read_csv('UrbanSound8K.csv')
+
+categories = df.groupby('classID')['class'].unique
+
 def prediction_audio(audiofile, model):
 
     audio_data, sample_rate = librosa.load(audiofile, res_type='kaiser_fast')
@@ -22,7 +24,7 @@ def prediction_audio(audiofile, model):
     predicted_label = np.argmax(model.predict(X), axis=-1)
     # predicted_class = le.inverse_transform(predicted_label)
 
-    return predicted_label[0]
+    return categories[predicted_label][0]
 
 st.title("Détection de coups de feu")