Python 读取 WAV 格式音频文件

Python 支持 WAV 文件的读写，实时的声音输入输出需要安装pyAudio，pyMedia进行 MP3 的解码和播放。

WAV 是 Microsoft 开发的一种‌无损数字音频文件格式，通常被用来保存未压缩的声音数据 (Pulse Code Modulation，PCM，脉冲编码调制)，以高保真音质著称。

WAV 有三个重要的参数：声道数、采样频率和量化位数。

声道数：单声道 (mono) 或者是双声道 (stereo)。
采样频率：每秒钟声音信号的采集次数，常用的有 8kHz、16kHz、32kHz、48kHz、11.025kHz、22.05kHz、44.1kHz 等。
量化位数：用多少 bit 表达一次采样所采集的数据，通常有 8bit、16bit、24bit 和 32bit 等。

CD 中所储存的声音信号是双声道、44.1kHz、16bit。

如果你需要自己录制和编辑声音文件，推荐使用 Audacity。它是一款开源的、跨平台、多声道的录音编辑软件。在工作中使用 Audacity 进行声音信号的录制，然后再输出成 wav 文件供 Python 程序处理。

1.C:\Windows\media

(base) yongqiang@yongqiang:~$ cd /mnt/f/yongqiang_work/ (base) yongqiang@yongqiang:/mnt/f/yongqiang_work$ ll total 260 drwxrwxrwx 1 yongqiang yongqiang 4096 Jun 4 00:47 ./ drwxrwxrwx 1 yongqiang yongqiang 4096 Jun 3 22:11 ../ -rwxrwxrwx 1 yongqiang yongqiang 191788 Sep 15 2018 Windows_Ding.wav* -rwxrwxrwx 1 yongqiang yongqiang 70060 Sep 15 2018 ding.wav* (base) yongqiang@yongqiang:/mnt/f/yongqiang_work$ (base) yongqiang@yongqiang:/mnt/f/yongqiang_work$ pwd /mnt/f/yongqiang_work (base) yongqiang@yongqiang:/mnt/f/yongqiang_work$

2. 读 wav 格式声音文件

#!/usr/bin/env python # -*- coding: utf-8 -*- # yongqiang cheng from __future__ import absolute_import from __future__ import division from __future__ import print_function import wave import numpy as np # WAV file audio_file = "/mnt/f/yongqiang_work/ding.wav" object = wave.open(audio_file, "rb") # (nchannels, sampwidth, framerate, nframes, comptype, compname) params = object.getparams() nchannels, sampwidth, framerate, nframes, comptype, compname = params[:6] print("nchannels = ", nchannels) print("sampwidth = ", sampwidth) print("framerate = ", framerate) print("nframes = ", nframes) print("comptype = ", comptype) print("compname = ", compname) # Returns number of audio channels (1 for mono, 2 for stereo). print("object.getnchannels() = ", object.getnchannels()) # Returns sample width in bytes. print("object.getsampwidth() = ", object.getsampwidth()) # Returns sampling frequency. print("object.getframerate() = ", object.getframerate()) # Returns number of audio frames. print("object.getnframes() = ", object.getnframes()) # Returns compression type ('NONE' is the only supported type). print("object.getcomptype() = ", object.getcomptype()) # Human-readable version of getcomptype(). Usually 'not compressed' parallels 'NONE'. print("object.getcompname() = ", object.getcompname()) # Reads and returns at most n frames of audio, as a bytes object. str_data = object.readframes(nframes) object.close()

/home/yongqiang/miniconda3/envs/tf_cpu_1.4.1/bin/python /home/yongqiang/pycharm_work/yongqiang.py nchannels = 2 sampwidth = 2 framerate = 44100 nframes = 17504 comptype = NONE compname = not compressed object.getnchannels() = 2 object.getsampwidth() = 2 object.getframerate() = 44100 object.getnframes() = 17504 object.getcomptype() = NONE object.getcompname() = not compressed Process finished with exit code 0

3. 读 wav 格式声音文件

#!/usr/bin/env python # -*- coding: utf-8 -*- # yongqiang cheng from __future__ import absolute_import from __future__ import division from __future__ import print_function import wave import numpy as np import matplotlib.pyplot as plt # WAV file audio_file = "/mnt/f/yongqiang_work/ding.wav" object = wave.open(audio_file, "rb") # (nchannels, sampwidth, framerate, nframes, comptype, compname) params = object.getparams() nchannels, sampwidth, framerate, nframes, comptype, compname = params[:6] print("nchannels =", nchannels) print("sampwidth =", sampwidth) print("framerate =", framerate) print("nframes =", nframes) print("comptype =", comptype) print("compname =", compname) # Returns number of audio channels (1 for mono, 2 for stereo). print("object.getnchannels() =", object.getnchannels()) # Returns sample width in bytes. print("object.getsampwidth() =", object.getsampwidth()) # Returns sampling frequency. print("object.getframerate() =", object.getframerate()) # Returns number of audio frames. print("object.getnframes() =", object.getnframes()) # Returns compression type ('NONE' is the only supported type). print("object.getcomptype() =", object.getcomptype()) # Human-readable version of getcomptype(). Usually 'not compressed' parallels 'NONE'. print("object.getcompname() =", object.getcompname()) # Reads and returns at most n frames of audio, as a bytes object. str_data = object.readframes(nframes) # nframes = 17504, channels = 2, sampwidth = 2 # str_data (bytes: 70016) = nframes * channels * sampwidth = 17504 * 2 * 2 = 70016 object.close() wave_data = np.fromstring(str_data, dtype=np.short) wave_data.shape = -1, 2 wave_data = wave_data.T time = np.arange(0, nframes) * (1.0 / framerate) plt.subplot(211) plt.plot(time, wave_data[0]) plt.xlabel("left channel - time (seconds)") plt.subplot(212) plt.plot(time, wave_data[1], c="g") plt.xlabel("right channel - time (seconds)") plt.show()

/home/yongqiang/miniconda3/envs/pt-1.4_py-3.6/bin/python /home/yongqiang/pycharm_work/yongqiang.py nchannels = 2 sampwidth = 2 framerate = 44100 nframes = 17504 comptype = NONE compname = not compressed object.getnchannels() = 2 object.getsampwidth() = 2 object.getframerate() = 44100 object.getnframes() = 17504 object.getcomptype() = NONE object.getcompname() = not compressed Process finished with exit code 0

Python 调用wave.open打开 wav 文件，注意需要使用"rb"(二进制模式) 打开文件：

audio_file = "/mnt/f/yongqiang_work/ding.wav" object = wave.open(audio_file, "rb")

open返回一个Wave_read类的实例，通过调用它的方法读取 wav 文件的格式和数据：

getparams：一次性返回所有的 wav 文件的格式信息，它返回的是一个组元 (tuple)：声道数，量化位数 (byte 单位)，采样频率，采样点数，压缩类型，压缩类型的描述。wave 模块只支持非压缩的数据，因此可以忽略最后两个信息。

# (nchannels, sampwidth, framerate, nframes, comptype, compname) params = object.getparams() nchannels, sampwidth, framerate, nframes, comptype, compname = params[:6]

nchannels, sampwidth, framerate, nframes, comptype, compname等方法可以单独返回 wav 文件的特定的信息。

readframes：读取声音数据，传递一个参数指定需要读取的长度 (以取样点为单位)，readframes返回的是二进制数据 (bytes)，在 Python 中用字符串表示二进制数据。

# Reads and returns at most n frames of audio, as a bytes object. str_data = object.readframes(nframes) # nframes = 17504, channels = 2, sampwidth = 2 # str_data (bytes: 70016) = nframes * channels * sampwidth = 17504 * 2 * 2 = 70016

接下来需要根据声道数和量化单位，将读取的二进制数据转换为一个可以计算的数组：

wave_data = np.fromstring(str_data, dtype=np.short)

通过fromstring函数将字符串转换为数组，通过其参数dtype指定转换后的数据格式，由于我们的声音格式是以两个字节表示一个取样值，因此采用short数据类型转换。现在得到的wave_data是一个一维的short类型的数组，但是因为我们的声音文件是双声道的，因此它由左右两个声道的取样交替构成：LRLRLRLR....LR(L 表示左声道的取样值，R 表示右声道取样值)。修改wave_data的sharp之后：

wave_data.shape = -1, 2

将其转置得到：

wave_data = wave_data.T

最后通过取样点数和取样频率计算出每个取样的时间：

time = np.arange(0, nframes) * (1.0 / framerate)

4. sample width in bytes

#!/usr/bin/env python # -*- coding: utf-8 -*- # yongqiang cheng from __future__ import absolute_import from __future__ import division from __future__ import print_function import wave import numpy as np import matplotlib.pyplot as plt # WAV file audio_file = "/mnt/f/yongqiang_work/ding.wav" object = wave.open(audio_file, "rb") # (nchannels, sampwidth, framerate, nframes, comptype, compname) params = object.getparams() nchannels, sampwidth, framerate, nframes, comptype, compname = params[:6] print("nchannels =", nchannels) print("sampwidth =", sampwidth) print("framerate =", framerate) print("nframes =", nframes) print("comptype =", comptype) print("compname =", compname) # Returns number of audio channels (1 for mono, 2 for stereo). print("object.getnchannels() =", object.getnchannels()) # Returns sample width in bytes. print("object.getsampwidth() =", object.getsampwidth()) # Returns sampling frequency. print("object.getframerate() =", object.getframerate()) # Returns number of audio frames. print("object.getnframes() =", object.getnframes()) # Returns compression type ('NONE' is the only supported type). print("object.getcomptype() =", object.getcomptype()) # Human-readable version of getcomptype(). Usually 'not compressed' parallels 'NONE'. print("object.getcompname() =", object.getcompname()) # Reads and returns at most n frames of audio, as a bytes object. str_data = object.readframes(nframes) # nframes = 17504, channels = 2, sampwidth = 2 # str_data (bytes: 70016) = nframes * channels * sampwidth = 17504 * 2 * 2 = 70016 num_bytes = len(str_data) # num_bytes = 70016 print("num_bytes =", num_bytes, "bytes") object.close() wave_data = np.fromstring(str_data, dtype=np.short) wave_data.shape = -1, 2 wave_data = wave_data.T time = np.arange(0, nframes) * (1.0 / framerate) plt.subplot(211) plt.plot(time, wave_data[0]) plt.xlabel("left channel - time (seconds)") plt.subplot(212) plt.plot(time, wave_data[1], c="g") plt.xlabel("right channel - time (seconds)") plt.show()

/home/yongqiang/miniconda3/envs/pt-1.4_py-3.6/bin/python /home/yongqiang/pytorch_work/end2end-asr-pytorch-example/yongqiang.py nchannels = 2 sampwidth = 2 framerate = 44100 nframes = 17504 comptype = NONE compname = not compressed object.getnchannels() = 2 object.getsampwidth() = 2 object.getframerate() = 44100 object.getnframes() = 17504 object.getcomptype() = NONE object.getcompname() = not compressed num_bytes = 70016 bytes Process finished with exit code 0

References

[1] Yongqiang Cheng (程永强), https://yongqiang.blog.csdn.net/