Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import tensorflow as tf
+import librosa
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Load the pre-trained model
+model = tf.keras.models.load_model("model.h5")
+
+# Function to process audio and make predictions
+def process_audio(audio_file):
+    # Load audio file
+    y, sr = librosa.load(audio_file, sr=16000)
+    
+    # Feature extraction
+    mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
+    mfcc = np.mean(mfcc, axis=1).reshape(1, -1)
+    
+    # Predict inhale/exhale using the model
+    prediction = model.predict(mfcc)
+    
+    # For demonstration, return the prediction and a waveform plot
+    plt.figure(figsize=(10, 4))
+    librosa.display.waveshow(y, sr=sr)
+    plt.title("Audio Waveform")
+    plt.xlabel("Time (s)")
+    plt.ylabel("Amplitude")
+    plt.savefig("waveform.png")
+    plt.close()
+    
+    return f"Prediction: {np.argmax(prediction)}", "waveform.png"
+
+# Define Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("### Breathe Training Application")
+    with gr.Row():
+        audio_input = gr.Audio(label="Upload or Record Audio", type="filepath")
+        result_output = gr.Textbox(label="Prediction Result")
+        waveform_output = gr.Image(label="Waveform")
+    submit_button = gr.Button("Analyze")
+    
+    submit_button.click(
+        fn=process_audio,
+        inputs=[audio_input],
+        outputs=[result_output, waveform_output]
+    )
+
+# Run the Gradio app
+demo.launch()