Update app.py

app.py

@@ -1,19 +1,11 @@
 import gradio as gr
-import librosa
 import numpy as np
 from spleeter.separator import Separator
-import threading
-import queue
-import matplotlib.pyplot as plt
 import soundfile as sf
-
-# Load the song
-def load_audio(file_path):
-    signal, sr = librosa.load(file_path, sr=None)
-    return signal, sr
+import base64
 
 # Spleeter separation
-def spleeter_separate(audio, sr):
+def spleeter_separate(audio):
     separator = Separator('spleeter:5stems')
     prediction = separator.separate(audio)
     return prediction['vocals'], prediction['accompaniment'], prediction['bass'], prediction['drums'], prediction['other']
@@ -27,92 +19,32 @@ def adjust_volume(stems, volumes):
     return adjusted_stems
 
 # Function to handle the separation and volume adjustment
-def process_audio(file_path, volumes, result_queue):
-    audio, sr = load_audio(file_path)
-    stems = spleeter_separate(audio, sr)
+def process_audio(audio, volumes):
+    stems = spleeter_separate(audio)
     adjusted_stems = adjust_volume(stems, volumes)
-    result_queue.put(adjusted_stems)
-
-# Multithreaded processing
-def process_audio_threaded(file_path, volumes, result_queue):
-    thread = threading.Thread(target=process_audio, args=(file_path, volumes, result_queue))
-    thread.start()
-
-# Gradio interface
-def separate_audio(file, vocals, accompaniment, bass, drums, other):
-    file_path = file[0]
-
-    volumes = [vocals, accompaniment, bass, drums, other]
-
-    result_queue = queue.Queue()
-    process_audio_threaded(file_path, volumes, result_queue)
-    adjusted_stems = result_queue.get()
-
-    # Reconstruct the audio with adjusted stems
     reconstructed_audio = sum(adjusted_stems)
-
     return reconstructed_audio.astype(np.float32)
 
-# Plot waveform and spectrogram
-def plot_audio(signal, sr, title):
-    plt.figure(figsize=(10, 6))
-    
-    # Waveform plot
-    plt.subplot(2, 1, 1)
-    librosa.display.waveplot(signal, sr=sr)
-    plt.title('Waveform')
-    
-    # Spectrogram plot
-    plt.subplot(2, 1, 2)
-    plt.specgram(signal, NFFT=2048, Fs=2, Fc=0, noverlap=128, cmap='inferno', sides='default', mode='default', scale='dB')
-    plt.title('Spectrogram')
-    
-    plt.tight_layout()
-    plt.suptitle(title, fontsize=14)
-    plt.show()
+# Gradio interface
+def separate_audio(audio, vocals, accompaniment, bass, drums, other):
+    audio = np.frombuffer(base64.b64decode(audio), dtype=np.float32)
+    volumes = [vocals, accompaniment, bass, drums, other]
+    reconstructed_audio = process_audio(audio, volumes)
+    return base64.b64encode(reconstructed_audio.tobytes()).decode()
 
 iface = gr.Interface(
     fn=separate_audio,
     inputs=[
-        gr.inputs.Audio(label="Audio file"),
+        gr.inputs.Audio(label="Audio file", type="file", accept="audio/*"),
         gr.inputs.Slider(0.0, 1.0, step=0.1, label="Vocals"),
         gr.inputs.Slider(0.0, 1.0, step=0.1, label="Accompaniment"),
         gr.inputs.Slider(0.0, 1.0, step=0.1, label="Bass"),
         gr.inputs.Slider(0.0, 1.0, step=0.1, label="Drums"),
         gr.inputs.Slider(0.0, 1.0, step=0.1, label="Other")
     ],
-    outputs=gr.outputs.Audio(type="numpy", label="Separated Audio"),
+    outputs=gr.outputs.Audio(label="Separated Audio", type="base64"),
     title="Song Stem Separation",
-    description="Isolate vocals, accompaniment, bass, and drums of any song using the Spleeter model.",
+    description="Isolate vocals, accompaniment, bass, and drums of any song using the Spleeter model."
 )
 
-# Add visualizations and support for different audio formats
-def visualize_and_save_audio(inputs, output):
-    audio_file = inputs[0]
-    vocals = inputs[1]
-    accompaniment = inputs[2]
-    bass = inputs[3]
-    drums = inputs[4]
-    other = inputs[5]
-    
-    # Load the original audio file
-    signal, sr = librosa.load(audio_file.name, sr=None)
-    
-    # Plot waveform and spectrogram of the original audio
-    plot_audio(signal, sr, "Original Audio")
-    
-    # Save the separated audio to a file
-    output_file = "separated_audio.wav"
-    sf.write(output_file, output.astype(np.float32), sr)
-    
-    # Load the separated audio file
-    separated_signal, separated_sr = librosa.load(output_file, sr=None)
-    
-    # Plot waveform and spectrogram of the separated audio
-    plot_audio(separated_signal, separated_sr, "Separated Audio")
-    
-    # Provide feedback to the user
-    print("Audio separated successfully! Separated audio saved to 'separated_audio.wav'.")
-
 iface.launch()
-