Update app.py

app.py

@@ -9,15 +9,97 @@ import matplotlib.pyplot as plt
 model = tf.keras.models.load_model("model.h5")
 
 # Function to process audio, predict, and generate results
-def process_audio(audio_file, inhale_duration, exhale_duration):
+def process_audio(audio_file):
     try:
-        # Calculate total time to stop recording (inhale + exhale)
-        total_duration = inhale_duration + exhale_duration
         # Load the audio file
         y, sr = librosa.load(audio_file, sr=16000)
         
-        # Ensure the audio is only processed for the total duration
-        y = y[:int(total_duration * sr)]
+        # Detect segments (e.g., using energy or silence)
+        intervals = librosa.effects.split(y, top_db=20)
+        
+        results = []
+        
+        plt.figure(figsize=(10, 4))
+        librosa.display.waveshow(y, sr=sr, alpha=0.5)
+        
+        # Process each segment
+        for i, (start, end) in enumerate(intervals):
+            segment = y[start:end]
+            duration = (end - start) / sr
+            
+            # Compute the amplitude (mean absolute value)
+            amplitude = np.mean(np.abs(segment))
+            
+            # Extract MFCC features
+            mfcc = librosa.feature.mfcc(y=segment, sr=sr, n_mfcc=13)
+            mfcc = np.mean(mfcc, axis=1).reshape(1, -1)
+            
+            # Predict inhale or exhale (override with amplitude logic)
+            prediction = model.predict(mfcc)
+            label_from_model = "Inhale" if np.argmax(prediction) == 0 else "Exhale"
+            
+            # Assign label based on amplitude
+            label = "Inhale" if amplitude > 0.05 else "Exhale"  # Threshold for exhale
+            
+            # Append results
+            results.append({
+                "Segment": i + 1,
+                "Type": label,
+                "Duration (s)": round(duration, 2),
+                "Amplitude": round(amplitude, 4)
+            })
+            
+            # Highlight segment on waveform with swapped colors
+            plt.axvspan(start / sr, end / sr, color='red' if label == "Inhale" else 'blue', alpha=0.3)
+        
+        # Save the waveform with highlighted segments
+        plt.title("Audio Waveform with Inhale/Exhale Segments")
+        plt.xlabel("Time (s)")
+        plt.ylabel("Amplitude")
+        plt.savefig("waveform_highlighted.png")
+        plt.close()
+        
+        # Format results as a table
+        result_table = "Segment\tType\tDuration (s)\tAmplitude\n" + "\n".join(
+            f"{row['Segment']}\t{row['Type']}\t{row['Duration (s)']}\t{row['Amplitude']}" for row in results
+        )
+        
+        return result_table, "waveform_highlighted.png"
+    
+    except Exception as e:
+        return f"Error: {str(e)}", None
+
+# Define Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("### Breathe Training Application")
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
+        result_output = gr.Textbox(label="Prediction Results (Table)")
+        waveform_output = gr.Image(label="Waveform with Highlighted Segments")
+    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() make user can add period of breathe in and out as they want the sum of both selection will be the time that record auto stop mport gradio as gr
+import tensorflow as tf
+import librosa
+import librosa.display
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Load the pre-trained model
+model = tf.keras.models.load_model("model.h5")
+
+# Function to process audio, predict, and generate results
+def process_audio(audio_file):
+    try:
+        # Load the audio file
+        y, sr = librosa.load(audio_file, sr=16000)
         
         # Detect segments (e.g., using energy or silence)
         intervals = librosa.effects.split(y, top_db=20)
@@ -79,17 +161,15 @@ with gr.Blocks() as demo:
     gr.Markdown("### Breathe Training Application")
     with gr.Row():
         audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
-        inhale_duration_input = gr.Number(label="Inhale Duration (s)", value=5, interactive=True)
-        exhale_duration_input = gr.Number(label="Exhale Duration (s)", value=5, interactive=True)
         result_output = gr.Textbox(label="Prediction Results (Table)")
         waveform_output = gr.Image(label="Waveform with Highlighted Segments")
     submit_button = gr.Button("Analyze")
     
     submit_button.click(
         fn=process_audio,
-        inputs=[audio_input, inhale_duration_input, exhale_duration_input],
+        inputs=[audio_input],
         outputs=[result_output, waveform_output]
     )
 
 # Run the Gradio app
-demo.launch()
+demo.launch()