PyAudio 回调函数只调用一次

Posted 2023-02-25

【中文标题】PyAudio 回调函数只调用一次

【英文标题】：PyAudio callback function called only once

【发布时间】：2020-12-27 15:14:03

【问题描述】：

我正在尝试使用 PyAudio 使用此处提供的非阻塞 IO 代码简单地重现 wav 文件：PyAudio documentation。

与文档不同，我尝试使用 numpy 输入数据而不是字节，所以我使用 librosa 来加载我的 .wav 文件，而不是文档中所示的 wave。

我的代码如下，它是自包含且可重现的，您只需将filename 更改为您想要重现的波形音频之一：

import pyaudio
import wave
import time
import numpy as np
import scipy.io.wavfile as sw
import librosa
import sys
from scipy.io.wavfile import write


############ Global variables ###################
filename = '../wav/The_Weeknd.wav' #Test file
#Conversion from np to pyAudio types
np_to_pa_format = 
    np.dtype('float32') : pyaudio.paFloat32,
    np.dtype('int32') : pyaudio.paInt32,
    np.dtype('int16') : pyaudio.paInt16,
    np.dtype('int8') : pyaudio.paInt8,
    np.dtype('uint8') : pyaudio.paUInt8

np_type_to_sample_width = 
    np.dtype('float32') : 4,
    np.dtype('int32') : 4,
    np.dtype('int16') : 3,
    np.dtype('int8') : 1,
    np.dtype('uint8') : 1

STEREO = 2 #channels
#################################################

# Simple class which reads an input test wav file and reproduce it in a real time fashion. Used to test real time functioning.
class Player:
    # Loading the input test file. Crop to 30 seconds length
    def __init__(self):
        self.input_array, self.sample_rate = librosa.load(filename, sr=44100, dtype=np.float32, offset = 30, duration=30)

        print(self.sample_rate)
        print(self.input_array.shape)
        self.cycle_count = 0


    def pyaudio_callback(self,in_data, frame_count, time_info, status):
        audio_size = np.shape(self.input_array)[0]
        #print(audio_size)
        print(frame_count)
        if frame_count*self.cycle_count > audio_size:
            # Processing is complete.
            print('processing complete')
            return (None, pyaudio.paComplete)
        elif frame_count*(self.cycle_count+1) > audio_size:
            # Last frame to process.
            print('1 left frame')
            frames_left = audio_size - frame_count*self.cycle_count
        else:
            # Every other frame.
            print('everyotherframe')
            frames_left = frame_count

        data = self.input_array[frame_count*self.cycle_count:frame_count*self.cycle_count+frames_left]
        write('test.wav', 44100, data) #Saves correctly the file!

        print(data.shape)
        out_data = data.tobytes()
        print('printing length: ',len(out_data))
        self.cycle_count+=1
        print(self.cycle_count)
        print(pyaudio.paContinue)
        return (out_data, pyaudio.paContinue)





    def start_non_blocking_processing(self, save_output=True, frame_count=2**20, listen_output=True):
        '''
        Non blocking mode works on a different thread, therefore, the main thread must be kept active with, for example:
            while processing():
                time.sleep(1)
        '''
        self.save_output = save_output
        self.frame_count = frame_count

        # Initiate PyAudio
        self.pa = pyaudio.PyAudio()
        # Open stream using callback
        self.stream = self.pa.open(format=np_to_pa_format[self.input_array.dtype],
                        channels=STEREO,
                        rate=self.sample_rate,
                        output=listen_output,
                        input=not listen_output,
                        stream_callback=self.pyaudio_callback,
                        frames_per_buffer=frame_count)

        # Start the stream
        self.stream.start_stream()


    def processing(self):
        '''
        Returns true if the PyAudio stream is still active in non blocking mode.
        MUST be called AFTER self.start_non_blocking_processing.
        '''
        return self.stream.is_active()

    def terminate_processing(self):
        '''
        Terminates stream opened by self.start_non_blocking_processing.
        MUST be called AFTER self.processing returns False.
        '''
        # Stop stream.
        self.stream.stop_stream()
        self.stream.close()

        # Close PyAudio.
        self.pa.terminate()

        # Resets count.
        self.cycle_count = 0
        # Resets output.
        self.output_array = np.array([[], []], dtype=self.input_array.dtype).T



if __name__ == "__main__":
    print('RUNNING MAIN')
    player = Player()
    player.start_non_blocking_processing()
    while(player.processing()):
        time.sleep(0.1)
    player.terminate_processing()

基本上我遵循了文档教程，但我以更面向对象的方式重新编写了代码（因为我需要它用于更大的项目）。

我能够重现音频，但我注意到：

它的音调高于应有的水平 它只再现一帧，变量pyaudio.paContinue 始终为0，因此我的代码只执行一个音频“窗口”。

我一直在寻找解决方案，但只有一个类似问题的答案（此处：callback called only once），我无法解决我的问题。

问题回顾：我的回调函数只调用了一次（因为pyaudio.paContinue 始终为0），我不知道如何解决这个问题。

注意：代码的灵感来自https://github.com/grupo-1-ASSD-E2/ASSD-TP4

编辑：我添加了一个测试写入来检查包含音频的 numpy 数组（代码中的data 变量）是否正确，并且正确。 write 函数正确生成了一个带有预期音频的 .wav 文件。

编辑 2：pyaudio.paContinue 的值为 0 似乎很正常，这是“继续处理”的预期行为，如此处所述：pyAudio Documentation。所以我真的不知道为什么我的音频在回调函数 1 次迭代后停止

【参考方案1】：

我解决了这个问题。当我使用 MONO 文件时，我在 pa.open 函数中将 channels 声明为 STEREO。 librosa.read 自动将输入 wav 转换为单声道，即使它们是立体声文件。所以基本上我的stream 对象期待 2 个通道（交错），但它只有 1 个。

完整的工作代码如下：

#https://realpython.com/playing-and-recording-sound-python/#pyaudio
import pyaudio
import wave
import time
import numpy as np
import scipy.io.wavfile as sw
import librosa
import sys
from scipy.io.wavfile import write


############ Global variables ###################
filename = '../wav/The_Weeknd.wav' #Test file
chunk = 512 #frame size
#Conversion from np to pyAudio types
np_to_pa_format = 
    np.dtype('float32') : pyaudio.paFloat32,
    np.dtype('int32') : pyaudio.paInt32,
    np.dtype('int16') : pyaudio.paInt16,
    np.dtype('int8') : pyaudio.paInt8,
    np.dtype('uint8') : pyaudio.paUInt8

np_type_to_sample_width = 
    np.dtype('float32') : 4,
    np.dtype('int32') : 4,
    np.dtype('int16') : 3,
    np.dtype('int8') : 1,
    np.dtype('uint8') : 1

STEREO = 2 #channels
#################################################

# Simple class which reads an input test wav file and reproduce it in a real time fashion. Used to test real time functioning.
class Player:
    # Loading the input test file. Crop to 30 seconds length
    def __init__(self):
        self.input_array, self.sample_rate = librosa.load(filename, sr=44100, dtype=np.float32, duration=60)

        #print(self.sample_rate)
        #print(self.input_array.shape)
        self.cycle_count = 0


    def pyaudio_callback(self,in_data, frame_count, time_info, status):
        audio_size = np.shape(self.input_array)[0]
        #print(audio_size)
        print('frame count: ', frame_count)

        if frame_count*self.cycle_count > audio_size:
            # Processing is complete.
            print('processing complete')
            return (None, pyaudio.paComplete)
        elif frame_count*(self.cycle_count+1) > audio_size:
            # Last frame to process.
            print('1 left frame')
            frames_left = audio_size - frame_count*self.cycle_count
        else:
            # Every other frame.
            print('everyotherframe')
            frames_left = frame_count

        data = self.input_array[frame_count*self.cycle_count:frame_count*self.cycle_count+frames_left]
        print('len of data', data.shape)

        #write('test.wav', 44100, data) #Saves correctly the file!
        out_data = data.astype(np.float32).tobytes()
        print('printing length: ',len(out_data))
        #print(out_data)
        self.cycle_count+=1
        print(self.cycle_count)
        print('pyaudio continue value: ',pyaudio.paContinue)
        return (out_data, pyaudio.paContinue)





    def start_non_blocking_processing(self, save_output=True, frame_count=2**10, listen_output=True):
        '''
        Non blocking mode works on a different thread, therefore, the main thread must be kept active with, for example:
            while processing():
                time.sleep(1)
        '''
        self.save_output = save_output
        self.frame_count = frame_count

        # Initiate PyAudio
        self.pa = pyaudio.PyAudio()
        # Open stream using callback
        self.stream = self.pa.open(format=np_to_pa_format[self.input_array.dtype],
                        channels=1,
                        rate=self.sample_rate,
                        output=listen_output,
                        input=not listen_output,
                        stream_callback=self.pyaudio_callback,
                        frames_per_buffer=frame_count)

        # Start the stream
        self.stream.start_stream()


    def processing(self):
        '''
        Returns true if the PyAudio stream is still active in non blocking mode.
        MUST be called AFTER self.start_non_blocking_processing.
        '''
        return self.stream.is_active()

    def terminate_processing(self):
        '''
        Terminates stream opened by self.start_non_blocking_processing.
        MUST be called AFTER self.processing returns False.
        '''
        # Stop stream.
        self.stream.stop_stream()
        self.stream.close()

        # Close PyAudio.
        self.pa.terminate()

        # Resets count.
        self.cycle_count = 0
        # Resets output.
        self.output_array = np.array([[], []], dtype=self.input_array.dtype).T



if __name__ == "__main__":
    print('RUNNING MAIN')
    player = Player()
    player.start_non_blocking_processing()
    while(player.processing()):
        time.sleep(0.1)
    player.terminate_processing()