如何使用 Pydub 更改音频播放速度？
How to change audio playback speed using Pydub?
我是音频编辑库的新手 - Pydub. I want to change some audio files' playback speed using Pydub(say .wav/mp3 format files), but I don't know how to make it. The only module I saw that could possibly deal with this problem is speedup module in effect.py。但是，没有关于我应该如何称呼它的解释。
谁能解释一下如何在 Pydub 中完成这项任务？非常感谢！
（一个相关问题：，但我想做的是在不改变音频质量的情况下改变播放速度。）
sound.set_frame_rate() 进行转换，它不应导致任何 "chipmunk effect"，但您可以做的是更改帧速率（不进行转换），然后将音频从那里转换回来到正常帧速率（如 44.1 kHz，"CD quality"）
from pydub import AudioSegment
sound = AudioSegment.from_file(…)
def speed_change(sound, speed=1.0):
# Manually override the frame_rate. This tells the computer how many
# samples to play per second
sound_with_altered_frame_rate = sound._spawn(sound.raw_data, overrides={
"frame_rate": int(sound.frame_rate * speed)
})
# convert the sound with altered frame rate to a standard frame rate
# so that regular playback programs will work right. They often only
# know how to play audio at standard frame rate (like 44.1k)
return sound_with_altered_frame_rate.set_frame_rate(sound.frame_rate)
slow_sound = speed_change(sound, 0.75)
fast_sound = speed_change(sound, 2.0)
这可以使用 pyrubberband 包来完成，它需要 rubberband 库，可以在保持音调和高质量的同时拉伸音频。我能够使用 brew 在 MacOS 上安装该库，在 Ubuntu 上使用 apt install 也是如此。对于极端拉伸，查看 PaulStretch
brew install rubberband
这只适用于 librosa 包
import librosa
import pyrubberband
import soundfile as sf
y, sr = librosa.load(filepath, sr=None)
y_stretched = pyrubberband.time_stretch(y, sr, 1.5)
sf.write(analyzed_filepath, y_stretched, sr, format='wav')
为了使 pyrubberband 在没有 librosa 的情况下直接与 pydub 的 AudioSegment 一起工作，我修改了这个函数：
def change_audioseg_tempo(audiosegment, tempo, new_tempo):
y = np.array(audiosegment.get_array_of_samples())
if audiosegment.channels == 2:
y = y.reshape((-1, 2))
sample_rate = audiosegment.frame_rate
tempo_ratio = new_tempo / tempo
print(tempo_ratio)
y_fast = pyrb.time_stretch(y, sample_rate, tempo_ratio)
channels = 2 if (y_fast.ndim == 2 and y_fast.shape[1] == 2) else 1
y = np.int16(y_fast * 2 ** 15)
new_seg = pydub.AudioSegment(y.tobytes(), frame_rate=sample_rate, sample_width=2, channels=channels)
return new_seg
from pydub import AudioSegment
from pydub import effects
root = r'audio.wav'
velocidad_X = 1.5 # No puede estar por debajo de 1.0
sound = AudioSegment.from_file(root)
so = sound.speedup(velocidad_X, 150, 25)
so.export(root[:-4] + '_Out.mp3', format = 'mp3')
我知道晚了，但我写了一个程序来将 mp3 转换为不同的播放速度。
首先，转换 .MP3 -> .Wav，因为 PYRubberBand 仅支持 .wav 格式。然后同时拉长时间和音调，避免花栗鼠效应。
import wave
import sys
from pydub import AudioSegment
#sound = AudioSegment.from_file("deviprasadgharpehai.mp3")
sound = AudioSegment.from_mp3(sys.argv[1])
sound.export("file.wav", format="wav")
print(sys.argv[1])
import soundfile as sf
import pyrubberband as pyrb
y, sr = sf.read("file.wav")
# Play back at extra low speed
y_stretch = pyrb.time_stretch(y, sr, 0.5)
# Play back extra low tones
y_shift = pyrb.pitch_shift(y, sr, 0.5)
sf.write("analyzed_filepathX5.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX5.wav")
sound.export("analyzed_filepathX5.mp3", format="mp3")
# Play back at low speed
y_stretch = pyrb.time_stretch(y, sr, 0.75)
# Play back at low tones
y_shift = pyrb.pitch_shift(y, sr, 0.75)
sf.write("analyzed_filepathX75.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX75.wav")
sound.export("analyzed_filepathX75.mp3", format="mp3")
# Play back at 1.5X speed
y_stretch = pyrb.time_stretch(y, sr, 1.5)
# Play back two 1.5x tones
y_shift = pyrb.pitch_shift(y, sr, 1.5)
sf.write("analyzed_filepathX105.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX105.wav")
sound.export("analyzed_filepathX105.mp3", format="mp3")
# Play back at same speed
y_stretch = pyrb.time_stretch(y, sr, 1)
# Play back two smae-tones
y_shift = pyrb.pitch_shift(y, sr, 1)
sf.write("analyzed_filepathXnormal.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathXnormal.wav")
sound.export("analyzed_filepathXnormal.mp3", format="mp3")
**确保安装**
Wave、AudioSegment、FFmpeg、PYRubberBand、Soundfile
使用这个运行,
python3 filename.py mp3filename.mp3
我是音频编辑库的新手 - Pydub. I want to change some audio files' playback speed using Pydub(say .wav/mp3 format files), but I don't know how to make it. The only module I saw that could possibly deal with this problem is speedup module in effect.py。但是，没有关于我应该如何称呼它的解释。
谁能解释一下如何在 Pydub 中完成这项任务？非常感谢！
（一个相关问题：
sound.set_frame_rate() 进行转换，它不应导致任何 "chipmunk effect"，但您可以做的是更改帧速率（不进行转换），然后将音频从那里转换回来到正常帧速率（如 44.1 kHz，"CD quality"）
from pydub import AudioSegment
sound = AudioSegment.from_file(…)
def speed_change(sound, speed=1.0):
# Manually override the frame_rate. This tells the computer how many
# samples to play per second
sound_with_altered_frame_rate = sound._spawn(sound.raw_data, overrides={
"frame_rate": int(sound.frame_rate * speed)
})
# convert the sound with altered frame rate to a standard frame rate
# so that regular playback programs will work right. They often only
# know how to play audio at standard frame rate (like 44.1k)
return sound_with_altered_frame_rate.set_frame_rate(sound.frame_rate)
slow_sound = speed_change(sound, 0.75)
fast_sound = speed_change(sound, 2.0)
这可以使用 pyrubberband 包来完成，它需要 rubberband 库，可以在保持音调和高质量的同时拉伸音频。我能够使用 brew 在 MacOS 上安装该库，在 Ubuntu 上使用 apt install 也是如此。对于极端拉伸，查看 PaulStretch
brew install rubberband
这只适用于 librosa 包
import librosa
import pyrubberband
import soundfile as sf
y, sr = librosa.load(filepath, sr=None)
y_stretched = pyrubberband.time_stretch(y, sr, 1.5)
sf.write(analyzed_filepath, y_stretched, sr, format='wav')
为了使 pyrubberband 在没有 librosa 的情况下直接与 pydub 的 AudioSegment 一起工作，我修改了这个函数：
def change_audioseg_tempo(audiosegment, tempo, new_tempo):
y = np.array(audiosegment.get_array_of_samples())
if audiosegment.channels == 2:
y = y.reshape((-1, 2))
sample_rate = audiosegment.frame_rate
tempo_ratio = new_tempo / tempo
print(tempo_ratio)
y_fast = pyrb.time_stretch(y, sample_rate, tempo_ratio)
channels = 2 if (y_fast.ndim == 2 and y_fast.shape[1] == 2) else 1
y = np.int16(y_fast * 2 ** 15)
new_seg = pydub.AudioSegment(y.tobytes(), frame_rate=sample_rate, sample_width=2, channels=channels)
return new_seg
from pydub import AudioSegment
from pydub import effects
root = r'audio.wav'
velocidad_X = 1.5 # No puede estar por debajo de 1.0
sound = AudioSegment.from_file(root)
so = sound.speedup(velocidad_X, 150, 25)
so.export(root[:-4] + '_Out.mp3', format = 'mp3')
我知道晚了，但我写了一个程序来将 mp3 转换为不同的播放速度。
首先，转换 .MP3 -> .Wav，因为 PYRubberBand 仅支持 .wav 格式。然后同时拉长时间和音调，避免花栗鼠效应。
import wave
import sys
from pydub import AudioSegment
#sound = AudioSegment.from_file("deviprasadgharpehai.mp3")
sound = AudioSegment.from_mp3(sys.argv[1])
sound.export("file.wav", format="wav")
print(sys.argv[1])
import soundfile as sf
import pyrubberband as pyrb
y, sr = sf.read("file.wav")
# Play back at extra low speed
y_stretch = pyrb.time_stretch(y, sr, 0.5)
# Play back extra low tones
y_shift = pyrb.pitch_shift(y, sr, 0.5)
sf.write("analyzed_filepathX5.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX5.wav")
sound.export("analyzed_filepathX5.mp3", format="mp3")
# Play back at low speed
y_stretch = pyrb.time_stretch(y, sr, 0.75)
# Play back at low tones
y_shift = pyrb.pitch_shift(y, sr, 0.75)
sf.write("analyzed_filepathX75.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX75.wav")
sound.export("analyzed_filepathX75.mp3", format="mp3")
# Play back at 1.5X speed
y_stretch = pyrb.time_stretch(y, sr, 1.5)
# Play back two 1.5x tones
y_shift = pyrb.pitch_shift(y, sr, 1.5)
sf.write("analyzed_filepathX105.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathX105.wav")
sound.export("analyzed_filepathX105.mp3", format="mp3")
# Play back at same speed
y_stretch = pyrb.time_stretch(y, sr, 1)
# Play back two smae-tones
y_shift = pyrb.pitch_shift(y, sr, 1)
sf.write("analyzed_filepathXnormal.wav", y_stretch, sr, format='wav')
sound = AudioSegment.from_wav("analyzed_filepathXnormal.wav")
sound.export("analyzed_filepathXnormal.mp3", format="mp3")
**确保安装**
Wave、AudioSegment、FFmpeg、PYRubberBand、Soundfile
使用这个运行,
python3 filename.py mp3filename.mp3