Python：从歌曲中获取频率

Question

我正在编写一个用 4 个灯泡制作灯光秀的代码，它们会根据歌曲切换组合。 因此，我必须接受一首歌的频率。 我找到了这段代码，它基本上就是我想要的。

# Read in a WAV and find the freq's
import pyaudio
import wave
import numpy as np

chunk = 2024

# open up a wave
wf = wave.open('Audio_3.wav', 'rb')
swidth = wf.getsampwidth()
RATE = wf.getframerate()
# use a Blackman window
window = np.blackman(chunk)
# open stream
p = pyaudio.PyAudio()
stream = p.open(format =
                p.get_format_from_width(wf.getsampwidth()),
                channels = wf.getnchannels(),
                rate = RATE,
                output = True)

# read some data
data = wf.readframes(chunk)
# play stream and find the frequency of each chunk
print(len(data))
print(chunk*swidth)
while len(data) == chunk*swidth:
    # write data out to the audio stream
    stream.write(data)
    # unpack the data and times by the hamming window
    indata = np.array(wave.struct.unpack("%dh"%(len(data)/swidth),\
                                         data))*window
    # Take the fft and square each value
    fftData=abs(np.fft.rfft(indata))**2
    # find the maximum
    which = fftData[1:].argmax() + 1
    # use quadratic interpolation around the max
    if which != len(fftData)-1:
        y0,y1,y2 = np.log(fftData[which-1:which+2:])
        x1 = (y2 - y0) * .5 / (2 * y1 - y2 - y0)
        # find the frequency and output it
        thefreq = (which+x1)*RATE/chunk
        print ("The freq is %f Hz." % (thefreq))
    else:
        thefreq = which*RATE/chunk
        print ("The freq is %f Hz." % (thefreq))
    # read some more data
    data = wf.readframes(chunk)
if data:
    stream.write(data)
stream.close()
p.terminate()

然而，问题是这段代码只适用于基本的声音。 当我为一首歌尝试此代码时，循环变为错误。 是否有从歌曲中获取频率的代码？ 还是有其他办法？

Answer 1

我认为立体声文件造成了麻烦，因为数据大小最终将是样本宽度 * num_samples * num_channels。 以下似乎有效，为 audacity 生成的 440Hz 音调提供了一致的 433+-1Hz（错误来自 fft 或来自 audacity 的发生器）

# Read in a WAV and find the freq's
import pyaudio
import wave
import numpy as np

chunk = 1024

# open up a wave

wf = wave.open('/home/jeremy/Music/wav1.wav', 'rb')
swidth = wf.getsampwidth()
RATE = wf.getframerate()
# use a Blackman window
window = np.blackman(chunk)
# open stream
p = pyaudio.PyAudio()
channels = wf.getnchannels()
stream = p.open(format =
                p.get_format_from_width(wf.getsampwidth()),
                channels = channels,
                rate = RATE,
                output = True)

# read some data
data = wf.readframes(chunk)
# play stream and find the frequency of each chunk
print('switdth {} chunk {} data {} ch {}'.format(swidth,chunk,len(data), channels))
while len(data) == chunk*swidth*channels:
    # write data out to the audio stream
    stream.write(data)
    # unpack the data and times by the hamming window
#    indata = np.array(wave.struct.unpack("%dh"%(len(data)/(swidth)),data))*window
    indata = np.fromstring(data, dtype='int16')
    # deinterleave, select 1 channel
    channel0 = indata[0::channels]

    # Take the fft and square each value
    fftData=abs(np.fft.rfft(indata))**2
    # find the maximum
    which = fftData[1:].argmax() + 1
    # use quadratic interpolation around the max
    if which != len(fftData)-1:
        y0,y1,y2 = np.log(fftData[which-1:which+2:])
        x1 = (y2 - y0) * .5 / (2 * y1 - y2 - y0)
        # find the frequency and output it
        thefreq = (which+x1)*RATE/chunk
        print ("The freq is %f Hz." % (thefreq))
    else:
        thefreq = which*RATE/chunk
        print ("The freq is %f Hz." % (thefreq))
    # read some more data
    data = wf.readframes(chunk)
if data:
    stream.write(data)
stream.close()
p.terminate()