Update app.py

app.py

@@ -4,19 +4,14 @@ import gradio as gr
 
 # Load your pre-trained model
 model = tf.keras.models.load_model('capuchin_bird_audio.h5')
-
-# Function to load and preprocess audio file
-def load_wav_mono(filename):
-    file_contents = tf.io.read_file(filename)
+class_names = ['It is a capuchin Bird','This Is Not A Capuchin bird']
+# Function to preprocess input for the model
+def test_preprocess_1(file_path):
+    file_contents = tf.io.read_file(file_path)
     wav, sample_rate = tf.audio.decode_wav(file_contents, desired_channels=1)
     wav = tf.squeeze(wav, axis=-1)
     sample_rate = tf.cast(sample_rate, dtype=tf.int64)
     wav = tfio.audio.resample(wav, rate_in=sample_rate, rate_out=16000)
-    return wav
-
-# Function to preprocess input for the model
-def test_preprocess_1(file_path):
-    wav = load_wav_mono(file_path)
     wav = wav[:48000]
     zero_padding = tf.zeros([48000] - tf.shape(wav), dtype=tf.float32)
     wav = tf.concat([zero_padding, wav], 0)
@@ -27,27 +22,29 @@ def test_preprocess_1(file_path):
     return spectrogram
 
 # Function to make predictions
-def predict_audio(file_path):
-    input_data = test_preprocess_1(file_path)
+def predict_audio(wav):
+    input_data = test_preprocess_1(wav)
     prediction = model.predict(input_data)
-    
+
     # Threshold logic
     if prediction > 0.5:
-        result = "Capuchin bird voice"
+        result = class_names[1]
     else:
-        result = "Not Capuchin bird voice"
-    
+        result = class_names[0]
+
     return result
 
+
 # Gradio Interface
 iface = gr.Interface(
     fn=predict_audio,
     title='Capuchin Bird Classification',
-    inputs=gr.Audio(sources=['upload'],type="filepath", label="Upload Audio File"),
-    outputs=outputs=gr.Textbox(),
-    live=True,
-
+    inputs=gr.Audio(sources=['upload'],label="Input Audio",type="filepath"),
+    outputs='text',
 )
 
 # Launch the interface on localhost
 iface.launch()
+
+# Launch the interface on localhost
+iface.launch()