用 pyaudio 录制麦克风
Record mic with pyaudio
我尝试用 pyaudio 录制我的麦克风。所以我使用示例程序：
import pyaudio
import wave
if __name__ == "__main__":
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
RECORD_SECONDS = 6
WAVE_OUTPUT_FILENAME = 'filename'
audio = pyaudio.PyAudio()
pa = pyaudio.PyAudio()
list_audio = []
for x in range(0, pa.get_device_count()):
info = pa.get_device_info_by_index(x)
print("info {0}".format(info))
# start Recording
stream = audio.open(format=FORMAT, channels=CHANNELS,
rate=RATE, input=True,
frames_per_buffer=CHUNK)
# sample_rate=RATE)
print("recording...")
print('---------------------------------')
print(int(RATE / CHUNK * RECORD_SECONDS))
print('*********************************')
frames = []
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
print("Recording . . .")
frames.append(data)
print("Recording finished. . .")
# stop Recording
stream.stop_stream()
stream.close()
audio.terminate()
waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
waveFile.setnchannels(CHANNELS)
waveFile.setsampwidth(2)
audio.get_sample_size(FORMAT)
waveFile.setframerate(RATE)
waveFile.writeframes(b''.join(frames))
waveFile.close()
当我 运行 它时，我的 wav 文件只有噪音。我在 ubuntu 18.04 上工作。
我认为这来自 pulse/alsa 兼容性。但是当我在Skype上使用我的麦克风时没有问题。
此外，当我尝试录制特定设备时，我收到该错误：
device {'index': 0, 'structVersion': 2, 'name': 'HDA Intel PCH: ALC293 Analog (hw:0,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 2, 'defaultLowInputLatency': 0.005804988662131519, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
....
device {'index': 4, 'structVersion': 2, 'name': 'HDA Intel PCH: HDMI 3 (hw:0,9)', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 5, 'structVersion': 2, 'name': 'HDA Intel PCH: HDMI 4 (hw:0,10)', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 6, 'structVersion': 2, 'name': 'AK5371: USB Audio (hw:1,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 0, 'defaultLowInputLatency': 0.008684807256235827, 'defaultLowOutputLatency': -1.0, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': -1.0, 'defaultSampleRate': 44100.0}
Chosen index: 6
device {'index': 7, 'structVersion': 2, 'name': 'HD USB CAMERA: Audio (hw:2,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 0, 'defaultLowInputLatency': 0.008684807256235827, 'defaultLowOutputLatency': -1.0, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': -1.0, 'defaultSampleRate': 44100.0}
device {'index': 8, 'structVersion': 2, 'name': 'Jabra SPEAK 510 USB: Audio (hw:3,0)', 'hostApi': 0, 'maxInputChannels': 1, 'maxOutputChannels': 2, 'defaultLowInputLatency': 0.0239375, 'defaultLowOutputLatency': 0.0239375, 'defaultHighInputLatency': 0.096, 'defaultHighOutputLatency': 0.096, 'defaultSampleRate': 16000.0}
device {'index': 9, 'structVersion': 2, 'name': 'sysdefault', 'hostApi': 0, 'maxInputChannels': 128, 'maxOutputChannels': 128, 'defaultLowInputLatency': 0.021333333333333333, 'defaultLowOutputLatency': 0.021333333333333333, 'defaultHighInputLatency': 0.021333333333333333, 'defaultHighOutputLatency': 0.021333333333333333, 'defaultSampleRate': 48000.0}
device {'index': 10, 'structVersion': 2, 'name': 'front', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 11, 'structVersion': 2, 'name': 'surround40', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 12, 'structVersion': 2, 'name': 'surround51', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 13, 'structVersion': 2, 'name': 'surround71', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 14, 'structVersion': 2, 'name': 'hdmi', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 15, 'structVersion': 2, 'name': 'pulse', 'hostApi': 0, 'maxInputChannels': 32, 'maxOutputChannels': 32, 'defaultLowInputLatency': 0.008707482993197279, 'defaultLowOutputLatency': 0.008707482993197279, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 16, 'structVersion': 2, 'name': 'dmix', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.021333333333333333, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.021333333333333333, 'defaultSampleRate': 48000.0}
device {'index': 17, 'structVersion': 2, 'name': 'default', 'hostApi': 0, 'maxInputChannels': 32, 'maxOutputChannels': 32, 'defaultLowInputLatency': 0.008707482993197279, 'defaultLowOutputLatency': 0.008707482993197279, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2048
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->capture, inParams, self->primeBuffers, hwParamsCapture, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2719
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2843
Traceback (most recent call last):
File "/home/xavier/dev/3003_mdt/module-test-gui/controller.py", line 165, in start_record_bag
stream_callback=self.new_frame)
File "/home/xavier/.local/lib/python3.6/site-packages/pyaudio.py", line 750, in open
stream = Stream(self, *args, **kwargs)
File "/home/xavier/.local/lib/python3.6/site-packages/pyaudio.py", line 441, in __init__
self._stream = pa.open(**arguments)
OSError: [Errno -9997] Invalid sample rate
我也尝试用pyQt收集我的数据，但没有好的结果：
def on_new_audio_data(self, buff: QtMultimedia.QAudioBuffer):
with self.mutex:
import ctypes
audio_data = AudioData()
length_array = buff.sampleCount()
byte_array = (ctypes.c_uint8 * length_array).from_address(buff.constData().__int__())
# val = struct.unpack('<BBh', byte_array)
byte_buffer = bytearray()
for short_index in range(0,len(byte_array)):
byte_buffer.append(byte_array[short_index])
每两个字节有一个零值...
您可以尝试看看您是否使用了正确的输入设备。将 input_device_index={the right input device} 参数添加到 audio.open.
您可以像这样检查设备的 ID：How to select a specific input device with PyAudio
import pyaudio
p = pyaudio.PyAudio()
info = p.get_host_api_info_by_index(0)
numdevices = info.get('deviceCount')
for i in range(0, numdevices):
if (p.get_device_info_by_host_api_device_index(0, i).get('maxInputChannels')) > 0:
print "Input Device id ", i, " - ", p.get_device_info_by_host_api_device_index(0, i).get('name')
我尝试用 pyaudio 录制我的麦克风。所以我使用示例程序：
import pyaudio
import wave
if __name__ == "__main__":
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
RECORD_SECONDS = 6
WAVE_OUTPUT_FILENAME = 'filename'
audio = pyaudio.PyAudio()
pa = pyaudio.PyAudio()
list_audio = []
for x in range(0, pa.get_device_count()):
info = pa.get_device_info_by_index(x)
print("info {0}".format(info))
# start Recording
stream = audio.open(format=FORMAT, channels=CHANNELS,
rate=RATE, input=True,
frames_per_buffer=CHUNK)
# sample_rate=RATE)
print("recording...")
print('---------------------------------')
print(int(RATE / CHUNK * RECORD_SECONDS))
print('*********************************')
frames = []
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
print("Recording . . .")
frames.append(data)
print("Recording finished. . .")
# stop Recording
stream.stop_stream()
stream.close()
audio.terminate()
waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
waveFile.setnchannels(CHANNELS)
waveFile.setsampwidth(2)
audio.get_sample_size(FORMAT)
waveFile.setframerate(RATE)
waveFile.writeframes(b''.join(frames))
waveFile.close()
当我 运行 它时，我的 wav 文件只有噪音。我在 ubuntu 18.04 上工作。 我认为这来自 pulse/alsa 兼容性。但是当我在Skype上使用我的麦克风时没有问题。
此外，当我尝试录制特定设备时，我收到该错误：
device {'index': 0, 'structVersion': 2, 'name': 'HDA Intel PCH: ALC293 Analog (hw:0,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 2, 'defaultLowInputLatency': 0.005804988662131519, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
....
device {'index': 4, 'structVersion': 2, 'name': 'HDA Intel PCH: HDMI 3 (hw:0,9)', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 5, 'structVersion': 2, 'name': 'HDA Intel PCH: HDMI 4 (hw:0,10)', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 6, 'structVersion': 2, 'name': 'AK5371: USB Audio (hw:1,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 0, 'defaultLowInputLatency': 0.008684807256235827, 'defaultLowOutputLatency': -1.0, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': -1.0, 'defaultSampleRate': 44100.0}
Chosen index: 6
device {'index': 7, 'structVersion': 2, 'name': 'HD USB CAMERA: Audio (hw:2,0)', 'hostApi': 0, 'maxInputChannels': 2, 'maxOutputChannels': 0, 'defaultLowInputLatency': 0.008684807256235827, 'defaultLowOutputLatency': -1.0, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': -1.0, 'defaultSampleRate': 44100.0}
device {'index': 8, 'structVersion': 2, 'name': 'Jabra SPEAK 510 USB: Audio (hw:3,0)', 'hostApi': 0, 'maxInputChannels': 1, 'maxOutputChannels': 2, 'defaultLowInputLatency': 0.0239375, 'defaultLowOutputLatency': 0.0239375, 'defaultHighInputLatency': 0.096, 'defaultHighOutputLatency': 0.096, 'defaultSampleRate': 16000.0}
device {'index': 9, 'structVersion': 2, 'name': 'sysdefault', 'hostApi': 0, 'maxInputChannels': 128, 'maxOutputChannels': 128, 'defaultLowInputLatency': 0.021333333333333333, 'defaultLowOutputLatency': 0.021333333333333333, 'defaultHighInputLatency': 0.021333333333333333, 'defaultHighOutputLatency': 0.021333333333333333, 'defaultSampleRate': 48000.0}
device {'index': 10, 'structVersion': 2, 'name': 'front', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 11, 'structVersion': 2, 'name': 'surround40', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 12, 'structVersion': 2, 'name': 'surround51', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 13, 'structVersion': 2, 'name': 'surround71', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 14, 'structVersion': 2, 'name': 'hdmi', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 8, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.005804988662131519, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 15, 'structVersion': 2, 'name': 'pulse', 'hostApi': 0, 'maxInputChannels': 32, 'maxOutputChannels': 32, 'defaultLowInputLatency': 0.008707482993197279, 'defaultLowOutputLatency': 0.008707482993197279, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
device {'index': 16, 'structVersion': 2, 'name': 'dmix', 'hostApi': 0, 'maxInputChannels': 0, 'maxOutputChannels': 2, 'defaultLowInputLatency': -1.0, 'defaultLowOutputLatency': 0.021333333333333333, 'defaultHighInputLatency': -1.0, 'defaultHighOutputLatency': 0.021333333333333333, 'defaultSampleRate': 48000.0}
device {'index': 17, 'structVersion': 2, 'name': 'default', 'hostApi': 0, 'maxInputChannels': 32, 'maxOutputChannels': 32, 'defaultLowInputLatency': 0.008707482993197279, 'defaultLowOutputLatency': 0.008707482993197279, 'defaultHighInputLatency': 0.034829931972789115, 'defaultHighOutputLatency': 0.034829931972789115, 'defaultSampleRate': 44100.0}
Expression 'paInvalidSampleRate' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2048
Expression 'PaAlsaStreamComponent_InitialConfigure( &self->capture, inParams, self->primeBuffers, hwParamsCapture, &realSr )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2719
Expression 'PaAlsaStream_Configure( stream, inputParameters, outputParameters, sampleRate, framesPerBuffer, &inputLatency, &outputLatency, &hostBufferSizeMode )' failed in 'src/hostapi/alsa/pa_linux_alsa.c', line: 2843
Traceback (most recent call last):
File "/home/xavier/dev/3003_mdt/module-test-gui/controller.py", line 165, in start_record_bag
stream_callback=self.new_frame)
File "/home/xavier/.local/lib/python3.6/site-packages/pyaudio.py", line 750, in open
stream = Stream(self, *args, **kwargs)
File "/home/xavier/.local/lib/python3.6/site-packages/pyaudio.py", line 441, in __init__
self._stream = pa.open(**arguments)
OSError: [Errno -9997] Invalid sample rate
我也尝试用pyQt收集我的数据，但没有好的结果：
def on_new_audio_data(self, buff: QtMultimedia.QAudioBuffer):
with self.mutex:
import ctypes
audio_data = AudioData()
length_array = buff.sampleCount()
byte_array = (ctypes.c_uint8 * length_array).from_address(buff.constData().__int__())
# val = struct.unpack('<BBh', byte_array)
byte_buffer = bytearray()
for short_index in range(0,len(byte_array)):
byte_buffer.append(byte_array[short_index])
每两个字节有一个零值...
您可以尝试看看您是否使用了正确的输入设备。将 input_device_index={the right input device} 参数添加到 audio.open.
您可以像这样检查设备的 ID：How to select a specific input device with PyAudio
import pyaudio
p = pyaudio.PyAudio()
info = p.get_host_api_info_by_index(0)
numdevices = info.get('deviceCount')
for i in range(0, numdevices):
if (p.get_device_info_by_host_api_device_index(0, i).get('maxInputChannels')) > 0:
print "Input Device id ", i, " - ", p.get_device_info_by_host_api_device_index(0, i).get('name')