Update app.py

app.py

@@ -5,9 +5,6 @@ from scipy.io import wavfile
 import gradio as gr
 from inference import EnsembleDemucsMDXMusicSeparationModel, predict_with_model
 import torch
-import librosa
-import librosa.display
-import matplotlib.pyplot as plt
 import time
 
 # 检查文件是否准备好
@@ -24,28 +21,6 @@ def check_file_readiness(filepath):
         time.sleep(0.5)
     return True
 
-# 生成音频的频谱图
-def generate_spectrogram(audio_file_path):
-    y, sr = librosa.load(audio_file_path)
-    plt.figure(figsize=(10, 4))
-    S = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=128, fmax=8000)
-    librosa.display.specshow(librosa.power_to_db(S, ref=np.max),
-                             y_axis='mel', fmax=8000, x_axis='time')
-    plt.colorbar(format='%+2.0f dB')
-    plt.title('Mel spectrogram')
-    plt.tight_layout()
-    image_path = tempfile.mktemp('.png')
-    plt.savefig(image_path)
-    plt.close()
-    return image_path
-
-# 为多个音频文件生成频谱图
-def generate_spectrograms(audio_files):
-    output_spectrograms = []
-    for audio_file in audio_files:
-        output_spectrograms.append(generate_spectrogram(audio_file))
-    return tuple(output_spectrograms)
-
 # 音乐分离的包装函数
 def separate_music_file_wrapper(uploaded_files, use_cpu, use_single_onnx, large_overlap, small_overlap, chunk_size, use_large_gpu):
     input_files = [uploaded_files.name]  # 获取上传文件的路径
@@ -96,14 +71,10 @@ def separate_music_file_wrapper(uploaded_files, use_cpu, use_single_onnx, large_
             wavfile.write(empty_file, 44100, empty_data.astype(np.int16))  # 转换为int16，因为wavfile不支持float32
             output_files_ready.append(empty_file)
 
-    # 在分离音频后立即生成频谱图
-    output_spectrograms = generate_spectrograms(output_files_ready)
-
     print(len(output_files_ready)) # 应输出6
-    print(len(output_spectrograms)) # 应输出6
 
     print("返回前")
-    return tuple(output_files_ready) + output_spectrograms
+    return tuple(output_files_ready)
     print("返回后")
 
 description = """
@@ -134,22 +105,16 @@ with gr.Blocks(theme=theme) as demo:
     process_button = gr.Button("处理音频")
 
     vocals = gr.Audio(label="人声")
-    vocals_spectrogram = gr.Image(label="人声频谱图")
     instrumental = gr.Audio(label="伴奏")
-    instrumental_spectrogram = gr.Image(label="伴奏频谱图")
     instrumental2 = gr.Audio(label="伴奏2")
-    instrumental2_spectrogram = gr.Image(label="伴奏2频谱图")
     bass = gr.Audio(label="贝斯")
-    bass_spectrogram = gr.Image(label="贝斯频谱图")
     drums = gr.Audio(label="鼓声")
-    drums_spectrogram = gr.Image(label="鼓声频谱图")
     other = gr.Audio(label="其他")
-    other_spectrogram = gr.Image(label="其他频谱图")
     
     process_button.click(
         separate_music_file_wrapper,
         inputs=[uploaded_file, use_cpu, use_single_onnx, large_overlap, small_overlap, chunk_size, use_large_gpu],
-        outputs=[vocals, instrumental, instrumental2, bass, drums, other, vocals_spectrogram, instrumental_spectrogram, instrumental2_spectrogram, bass_spectrogram, drums_spectrogram, other_spectrogram],
+        outputs=[vocals, instrumental, instrumental2, bass, drums, other],
     )
 
 demo.queue().launch(debug=True, share=False)