我刚刚用 scipy 读取了一个 wav 文件，现在我想使用 matplotlib 制作文件的绘图，在“y 比例”上我想查看幅度，在“x 比例”上我想查看帧数！任何帮助我该怎么做？谢谢！
from scipy.io.wavfile import read
import numpy as np
from numpy import*
import matplotlib.pyplot as plt
a=read("C:/Users/Martinez/Desktop/impulso.wav")
print a
您可以调用 wave lib 来读取音频文件。
要绘制波形，请使用 matplotlib 中的“plot”函数
import matplotlib.pyplot as plt
import numpy as np
import wave
import sys
spf = wave.open("wavfile.wav", "r")
# Extract Raw Audio from Wav File
signal = spf.readframes(-1)
signal = np.fromstring(signal, "Int16")
# If Stereo
if spf.getnchannels() == 2:
print("Just mono files")
sys.exit(0)
plt.figure(1)
plt.title("Signal Wave...")
plt.plot(signal)
plt.show()
你会有类似的东西：
要以秒为单位绘制 x 轴，您需要获取帧速率并除以信号的大小，您可以使用 numpy 的 linspace 函数创建一个与音频文件大小呈线性间隔的时间向量，最后您可以再次使用 plot喜欢plt.plot(Time,signal)
import matplotlib.pyplot as plt
import numpy as np
import wave
import sys
spf = wave.open("Animal_cut.wav", "r")
# Extract Raw Audio from Wav File
signal = spf.readframes(-1)
signal = np.fromstring(signal, "Int16")
fs = spf.getframerate()
# If Stereo
if spf.getnchannels() == 2:
print("Just mono files")
sys.exit(0)
Time = np.linspace(0, len(signal) / fs, num=len(signal))
plt.figure(1)
plt.title("Signal Wave...")
plt.plot(Time, signal)
plt.show()
以秒为单位的新绘图 x 轴：
或者，如果您想使用 SciPy，您还可以执行以下操作：
from scipy.io.wavfile import read
import matplotlib.pyplot as plt
# read audio samples
input_data = read("Sample.wav")
audio = input_data[1]
# plot the first 1024 samples
plt.plot(audio[0:1024])
# label the axes
plt.ylabel("Amplitude")
plt.xlabel("Time")
# set the title
plt.title("Sample Wav")
# display the plot
plt.show()
根据@ederwander 的回答，这是一个也可以处理立体声输入的版本
import matplotlib.pyplot as plt
import numpy as np
import wave
file = 'test.wav'
with wave.open(file,'r') as wav_file:
#Extract Raw Audio from Wav File
signal = wav_file.readframes(-1)
signal = np.fromstring(signal, 'Int16')
#Split the data into channels
channels = [[] for channel in range(wav_file.getnchannels())]
for index, datum in enumerate(signal):
channels[index%len(channels)].append(datum)
#Get time from indices
fs = wav_file.getframerate()
Time=np.linspace(0, len(signal)/len(channels)/fs, num=len(signal)/len(channels))
#Plot
plt.figure(1)
plt.title('Signal Wave...')
for channel in channels:
plt.plot(Time,channel)
plt.show()
这是绘制波形文件的波形和频谱的代码
import wave
import numpy as np
import matplotlib.pyplot as plt
signal_wave = wave.open('voice.wav', 'r')
sample_rate = 16000
sig = np.frombuffer(signal_wave.readframes(sample_rate), dtype=np.int16)
对于波形文件的整个片段
sig = sig[:]
对于波形文件的部分片段
sig = sig[25000:32000]
分离立体声通道
left, right = data[0::2], data[1::2]
绘制波形 (plot_a) 和频谱 (plot_b)
plt.figure(1)
plot_a = plt.subplot(211)
plot_a.plot(sig)
plot_a.set_xlabel('sample rate * time')
plot_a.set_ylabel('energy')
plot_b = plt.subplot(212)
plot_b.specgram(sig, NFFT=1024, Fs=sample_rate, noverlap=900)
plot_b.set_xlabel('Time')
plot_b.set_ylabel('Frequency')
plt.show()
只是一个观察（我不能添加评论）。
您将收到以下消息：
DeprecationWarning：不推荐使用数字样式的类型代码，将来会导致错误。
不要将 np.fromstring 与二进制文件一起使用。而不是 signal = np.fromstring(signal, 'Int16')，最好使用 signal = np.frombuffer(signal, dtype='int16')。
这是处理单声道/立体声和 8 位/16 位 PCM 的版本。
import matplotlib.pyplot as plt
import numpy as np
import wave
file = 'test.wav'
wav_file = wave.open(file,'r')
#Extract Raw Audio from Wav File
signal = wav_file.readframes(-1)
if wav_file.getsampwidth() == 1:
signal = np.array(np.frombuffer(signal, dtype='UInt8')-128, dtype='Int8')
elif wav_file.getsampwidth() == 2:
signal = np.frombuffer(signal, dtype='Int16')
else:
raise RuntimeError("Unsupported sample width")
# http://schlameel.com/2017/06/09/interleaving-and-de-interleaving-data-with-python/
deinterleaved = [signal[idx::wav_file.getnchannels()] for idx in range(wav_file.getnchannels())]
#Get time from indices
fs = wav_file.getframerate()
Time=np.linspace(0, len(signal)/wav_file.getnchannels()/fs, num=len(signal)/wav_file.getnchannels())
#Plot
plt.figure(1)
plt.title('Signal Wave...')
for channel in deinterleaved:
plt.plot(Time,channel)
plt.show()
我想我可以把它放在评论中，但是基于@ederwander 和@TimSC 的答案，我想做一些更精细（如详细）和美观的东西。下面的代码创建了我认为非常好的立体声或单声道波形文件（我不需要标题，所以我只是将其注释掉，也不需要 show 方法 - 只需要保存图像文件） .
这是一个渲染的立体 wav 示例：
和代码，与我提到的差异：
import matplotlib.pyplot as plt
import numpy as np
import wave
file = '/Path/to/my/audio/file/DeadMenTellNoTales.wav'
wav_file = wave.open(file,'r')
#Extract Raw Audio from Wav File
signal = wav_file.readframes(-1)
if wav_file.getsampwidth() == 1:
signal = np.array(np.frombuffer(signal, dtype='UInt8')-128, dtype='Int8')
elif wav_file.getsampwidth() == 2:
signal = np.frombuffer(signal, dtype='Int16')
else:
raise RuntimeError("Unsupported sample width")
# http://schlameel.com/2017/06/09/interleaving-and-de-interleaving-data-with-python/
deinterleaved = [signal[idx::wav_file.getnchannels()] for idx in range(wav_file.getnchannels())]
#Get time from indices
fs = wav_file.getframerate()
Time=np.linspace(0, len(signal)/wav_file.getnchannels()/fs, num=len(signal)/wav_file.getnchannels())
plt.figure(figsize=(50,3))
#Plot
plt.figure(1)
#don't care for title
#plt.title('Signal Wave...')
for channel in deinterleaved:
plt.plot(Time,channel, linewidth=.125)
#don't need to show, just save
#plt.show()
plt.savefig('/testing_folder/deadmentellnotales2d.png', dpi=72)
我想出了一个更灵活、更高效的解决方案：
import matplotlib.pyplot as plt
import numpy as np
import wave
import math
file = 'audiofile.wav'
with wave.open(file,'r') as wav_file:
num_channels = wav_file.getnchannels()
frame_rate = wav_file.getframerate()
downsample = math.ceil(frame_rate * num_channels / 2) # Get two samples per second!
process_chunk_size = 600000 - (600000 % frame_rate)
signal = None
waveform = np.array([])
while signal is None or signal.size > 0:
signal = np.frombuffer(wav_file.readframes(process_chunk_size), dtype='int16')
# Take mean of absolute values per 0.5 seconds
sub_waveform = np.nanmean(
np.pad(np.absolute(signal), (0, ((downsample - (signal.size % downsample)) % downsample)), mode='constant', constant_values=np.NaN).reshape(-1, downsample),
axis=1
)
waveform = np.concatenate((waveform, sub_waveform))
#Plot
plt.figure(1)
plt.title('Waveform')
plt.plot(waveform)
plt.show()