保存的 .wav 文件没有数据

Question

我制作了一个程序来记录文件并将它们保存到文件目录中，它确实可以正确保存它们。但是，当我尝试打开它并查看录制的内容时，我发现它没有存储音频数据。我不确定我做错了什么。请看一下，让我知道。

from playsound import playsound
from random import randrange
import pyttsx3
from datetime import datetime
import pyaudio
import speech_recognition as sr
import requests
import wave
import numpy as np
import sounddevice as sd
import math
import time
import os
import sys
import sounddevice as sd
from scipy.io.wavfile import write
import struct
def voiceDetection():
    SoundThreshHold = 50
    TimeoutLength = 5
    chunk = 1024  
    FORMAT = pyaudio.paInt16
    CHANNELS = 2 #Basicly audio output
    RATE = 16000 #Rate at which you sample
    f_name_directory = r"C:\Users\x\OneDrive\Desktop\Record"
    def rms(data):
       count = len(data)/2
       format = "%dh"%(count)
       shorts = struct.unpack( format, data )
       sum_squares = 0.0
       for sample in shorts:
           n = sample * (1.0/32768)
           sum_squares += n*n
       return math.sqrt( sum_squares / count)*1000
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT,
                     channels=CHANNELS,
                     rate=RATE,
                     input=True,
                     output=True,
                     frames_per_buffer=chunk)
    currentTime = time.time()
    end = time.time() + TimeoutLength
    frames = []
    while currentTime < end:
       currentTime = time.time()
       data = stream.read(chunk)
       if rms(data) >= SoundThreshHold:
          #print(rms(data))
          end = time.time() + TimeoutLength
          frames.append(data)
          n_files = len(os.listdir(f_name_directory))
          filename = os.path.join(f_name_directory,'{}.wav'.format(n_files))
          wf = wave.open(filename,'wb')
          wf.setnchannels(CHANNELS)
          wf.setsampwidth(p.get_sample_size(FORMAT))
          wf.setframerate(RATE)
          wf.writeframes(data)
          wf.close()
          print('Written to file: {}'.format(filename))
    stream.stop_stream()
    stream.close()
    p.terminate()
voiceDetection()

Answer 1

当前代码为每个块写入一个单独的 WAV 文件，并且始终使用相同的名称，因此该文件会覆盖为前一个块编写的任何 WAV。您可能打算在循环之前调用 wave.open 一次，在循环之后调用 wf.close，以便为整个会话编写一个 WAV。

---

编辑： 在音频录制过程中散布文件 IO 可能会导致在不丢失样本的情况下正确录制的开销太大。您可以尝试缓冲内存中的所有样本，然后一次全部写入 WAV。在pyaudio homepage上，有一个“录制”的例子，可以录制几秒的音频，然后写成WAV文件：

"""PyAudio example: Record a few seconds of audio and save to a WAVE file."""

import pyaudio
import wave

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"

p = pyaudio.PyAudio()

stream = p.open(format=FORMAT,
                channels=CHANNELS,
                rate=RATE,
                input=True,
                frames_per_buffer=CHUNK)

print("* recording")

frames = []

for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)

print("* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()

作为一般说明，请注意，不幸的是（标准 CPython）Python 解释器在真正同时执行线程方面的能力有限，这使得 Python 对于实时音频应用程序来说是一种糟糕的语言（另请参阅 Does python support multiprocessor/multicore programming?）。根据您的项目目标，您可能希望切换到 C++ 并使用 portaudio C 库（pyaudio 所基于的库）。