added comparison

app.py

@@ -2,11 +2,32 @@ from plotly.subplots import make_subplots
 import plotly.graph_objects as go
 import gradio as gr
 import numpy as np
+import itertools
 import librosa
 import os
 
 example_dir = "Examples"
 example_files = [os.path.join(example_dir, f) for f in os.listdir(example_dir) if f.endswith(('.wav', '.mp3', '.ogg'))]
+example_pairs = [list(pair) for pair in itertools.combinations(example_files, 2)][:25]  # Limit to 5 pairs
+print("Example Pairs: ", example_pairs)
+# GENERAL HELPER FUNCTIONS
+def getaudiodata(audio:gr.Audio)->tuple[int,np.ndarray]:
+    # Extract audio data and sample rate
+    sr, audiodata = audio
+
+    # Ensure audiodata is a numpy array
+    if not isinstance(audiodata, np.ndarray):
+        audiodata = np.array(audiodata)
+
+    # Check if audio is mono or stereo
+    if len(audiodata.shape) > 1:
+        # If stereo, convert to mono by averaging channels
+        audiodata = np.mean(audiodata, axis=1)
+
+    audiodata = np.astype(audiodata, np.float16)
+
+    return sr, audiodata
+
 
 # HELPER FUNCTIONS FOR SINGLE AUDIO ANALYSIS
 def getBeats(audiodata:np.ndarray, sr:int):
@@ -45,31 +66,51 @@ def plotCombined(audiodata, sr):
         row=2, col=1
     )
 
+
     # Update layout
     fig.update_layout(
         height=800, width=900,
         title_text="Audio Analysis",
     )
+
     fig.update_xaxes(title_text="Time (s)", row=2, col=1)
     fig.update_yaxes(title_text="Amplitude", row=1, col=1)
     fig.update_yaxes(title_text="Frequency (Hz)", type="log", row=2, col=1)
 
     return fig
 
+def plotbeatshist(tempo, beattimes):
+    # Calculate beat durations
+    beat_durations = np.diff(beattimes)
+    
+    # Create histogram
+    fig = go.Figure()
+    fig.add_trace(go.Histogram(
+        x=beat_durations,
+        nbinsx=60,  # You can adjust the number of bins as needed
+        name='Beat Durations'
+    ))
+    
+    # Add vertical line for average beat duration
+    avg_duration = 60 / tempo  # Convert tempo (BPM) to seconds
+    fig.add_vline(x=avg_duration, line_dash="dash", line_color="red",
+                  annotation_text=f"Average: {avg_duration:.2f}s", 
+                  annotation_position="top right")
+    
+    # Update layout
+    fig.update_layout(
+        title_text='Histogram of Beat Durations',
+        xaxis_title_text='Beat Duration (seconds)',
+        yaxis_title_text='Count',
+        bargap=0.05,  # gap between bars
+    )
+    
+    return fig
+
 def analyze_single(audio:gr.Audio):
     # Extract audio data and sample rate
-    sr, audiodata = audio
-
-    # Ensure audiodata is a numpy array
-    if not isinstance(audiodata, np.ndarray):
-        audiodata = np.array(audiodata)
+    sr, audiodata = getaudiodata(audio)
 
-    # Check if audio is mono or stereo
-    if len(audiodata.shape) > 1:
-        # If stereo, convert to mono by averaging channels
-        audiodata = np.mean(audiodata, axis=1)
-
-    audiodata = np.astype(audiodata, np.float16)
 
     # Now you have:
     # - audiodata: a 1D numpy array containing the audio samples
@@ -89,6 +130,7 @@ def analyze_single(audio:gr.Audio):
 
     tempo, beattimes = getBeats(audiodata, sr)
     spectogram_wave = plotCombined(audiodata, sr)
+    beats_histogram = plotbeatshist(tempo, beattimes)
 
     # Return your analysis results
     results = f"""
@@ -96,14 +138,88 @@ def analyze_single(audio:gr.Audio):
     - Sample rate: {sr} Hz
     - Mean Zero Crossing Rate: {np.mean(zcr):.4f}
     - Mean RMS Energy: {np.mean(rms):.4f}
-    - Tempo: {tempo}
+    - Tempo: {tempo:.4f}
     - Beats: {beattimes}
+    - Beat durations: {np.diff(beattimes)}
+    - Mean Beat Duration: {np.mean(np.diff(beattimes)):.4f}
     """
-    return results, spectogram_wave
+    return results, spectogram_wave, beats_histogram
 #-----------------------------------------------
 #-----------------------------------------------
 
 # HELPER FUNCTIONS FOR DUAL AUDIO ANALYSIS
+def analyze_double(audio1:gr.Audio, audio2:gr.Audio):
+    
+    sr1, audiodata1 = getaudiodata(audio1)
+    sr2, audiodata2 = getaudiodata(audio2)
+
+
+    combinedfig = plotCombineddouble(audiodata1, sr1, audiodata2, sr2)
+    return combinedfig
+
+def plotCombineddouble(audiodata1, sr1, audiodata2, sr2):
+    # Create subplots
+    fig = make_subplots(rows=2, cols=2, shared_xaxes=True, vertical_spacing=0.1,
+                        subplot_titles=('Audio Waveform', 'Spectrogram'))
+
+    # Waveform plot
+    time = (np.arange(0, len(audiodata1)) / sr1)*2
+    fig.add_trace(
+        go.Scatter(x=time, y=audiodata1, mode='lines', name='Waveform', line=dict(color='blue', width=1)),
+        row=1, col=1
+    )
+
+    # Spectrogram plot
+    D = librosa.stft(audiodata1)
+    S_db = librosa.amplitude_to_db(np.abs(D), ref=np.max)
+    times = librosa.times_like(S_db)
+    freqs = librosa.fft_frequencies(sr=sr1)
+
+    fig.add_trace(
+        go.Heatmap(z=S_db, x=times, y=freqs, colorscale='Viridis', 
+                   zmin=S_db.min(), zmax=S_db.max(), colorbar=dict(title='Magnitude (dB)')),
+        row=2, col=1
+    )
+
+    # Waveform plot
+    time = (np.arange(0, len(audiodata2)) / sr2)*2
+    fig.add_trace(
+        go.Scatter(x=time, y=audiodata2, mode='lines', name='Waveform', line=dict(color='blue', width=1)),
+        row=1, col=2
+    )
+
+    # Spectrogram plot
+    D = librosa.stft(audiodata2)
+    S_db = librosa.amplitude_to_db(np.abs(D), ref=np.max)
+    times = librosa.times_like(S_db)
+    freqs = librosa.fft_frequencies(sr=sr2)
+
+    fig.add_trace(
+        go.Heatmap(z=S_db, x=times, y=freqs, colorscale='Viridis', 
+                   zmin=S_db.min(), zmax=S_db.max(), colorbar=dict(title='Magnitude (dB)')),
+        row=2, col=2
+    )
+
+
+
+
+
+    # Update layout
+    fig.update_layout(
+        height=800, width=1200,
+        title_text="Audio Analysis",
+    )
+
+    fig.update_xaxes(title_text="Time (s)", row=2, col=1)
+    fig.update_yaxes(title_text="Amplitude", row=1, col=1)
+    fig.update_yaxes(title_text="Frequency (Hz)", type="log", row=2, col=1)
+
+    fig.update_xaxes(title_text="Time (s)", row=2, col=2)
+    fig.update_yaxes(title_text="Amplitude", row=1, col=2)
+    fig.update_yaxes(title_text="Frequency (Hz)", type="log", row=2, col=2)
+
+    return fig
+
 
 
 
@@ -129,8 +245,9 @@ with gr.Blocks() as app:
 
         results = gr.Markdown()
         spectogram_wave = gr.Plot()
+        beats_histogram = gr.Plot()
 
-        analyzebtn.click(analyze_single, audiofile, [results, spectogram_wave])
+        analyzebtn.click(analyze_single, audiofile, [results, spectogram_wave, beats_histogram])
 
         gr.Examples(
             examples=example_files,
@@ -140,6 +257,11 @@ with gr.Blocks() as app:
             cache_examples=False
         )
 
+        gr.Markdown("""### Open TODO's
+        - Create Histogram for Beat durations
+        - classify Beat's into S1 and S2
+        - synthesise the mean Beat S1 & S2""")
+
     with gr.Tab("Two Audios"):
 
         with gr.Row():
@@ -157,6 +279,16 @@ with gr.Blocks() as app:
             results2 = gr.Markdown()
             spectogram_wave2 = gr.Plot()
 
+        analyzebtn2.click(analyze_double, inputs=[audioone,audiotwo], outputs=spectogram_wave2)
+
+        # Add gr.Examples for the Two Audios tab
+        gr.Examples(
+            examples=example_pairs,  # Create pairs of the same file for demonstration
+            inputs=[audioone, audiotwo],
+            outputs=spectogram_wave2,
+            fn=analyze_double,
+            cache_examples=False
+        )
 
 if __name__ == "__main__":
     app.launch()