add mp4_to_mp3.py

python/util/mp4_to_mp3.py

@@ -0,0 +1,33 @@
+from moviepy.editor import *
+import sys
+# print('argv[1]:' + str(sys.argv[1]))
+import os
+from pydub import AudioSegment
+
+
+def mp4_to_mp3(mp4_uri):
+	# Load the mp4 file
+	video = VideoFileClip(mp4_uri)
+
+	# Extract audio from video
+	video.audio.write_audiofile(mp4_uri + ".mp3")
+
+
+def audio_to_wav(wav_uri, out_sample_rate=16000):
+    src = wav_uri
+    dst = wav_uri + ".wav"
+    if os.path.exists(dst): os.remove(dst)
+
+    # convert wav to mp3
+    sound = AudioSegment.from_file(src)
+    sound = sound.set_frame_rate(out_sample_rate)
+    sound.export(dst, format="wav")
+
+    print(' audio_to_wav: ', str(dst))
+    return dst
+
+sys.argv
+if len(sys.argv) > 1:
+    res = mp4_to_mp3(sys.argv[1])
+else:
+    print(' usage: python mp4_to_mp3.py /path/to/mp4_file ')

python/util/plt_util.py

@@ -44,7 +44,7 @@ def plt_mfcc(single_channel, sample_rate):
     log_mel_spec = librosa.power_to_db(mel_spec)
     plt.figure()
     librosa.display.specshow(log_mel_spec, sr=sample_rate, x_axis='time', y_axis='mel')
-    plt.colorbar(format='%+2.0f dB')  # 右边的色度条
+    # plt.colorbar(format='%+2.0f dB')  # 右边的色度条
     plt.title('MFCC')
 
     # plot to image
@@ -75,7 +75,7 @@ def plt_mfcc2(wav_pathname, sample_rate):
     plt.title('mel power spectrogram')
 
     # draw a color bar
-    plt.colorbar(format='%+02.0f dB')
+    # plt.colorbar(format='%+02.0f dB')
 
     # Make the figure layout compact
     plt.tight_layout()