Python 给出函数变量的值
我有一个VoiceActivityDetector的代码，想要给出函数中的值speech_ratio 我尝试设置一个新函数来打印值Python 给出函数变量的值,python,Python,我有一个VoiceActivityDetector的代码，想要给出函数中的值speech_ratio 我尝试设置一个新函数来打印值 def __init__(self, wave_input_filename): self._read_wav(wave_input_filename)._convert_to_mono() self.sample_window = 0.02 #20 ms self.sample_overlap = 0.01 #10
def __init__(self, wave_input_filename):
self._read_wav(wave_input_filename)._convert_to_mono()
self.sample_window = 0.02 #20 ms
self.sample_overlap = 0.01 #10ms
self.speech_window = 0.5 #half a second
self.speech_energy_threshold = 0.6 #60% of energy in voice band
self.speech_start_band = 300
self.speech_end_band = 3000
#self.speech_ratio = 0
def detect_speech(self):
""" Detects speech regions based on ratio between speech band energy
and total energy.
Output is array of window numbers and speech flags (1 - speech, 0 - nonspeech).
"""
detected_windows = np.array([])
sample_window = int(self.rate * self.sample_window)
sample_overlap = int(self.rate * self.sample_overlap)
data = self.data
sample_start = 0
start_band = self.speech_start_band
end_band = self.speech_end_band
while (sample_start < (len(data) - sample_window)):
sample_end = sample_start + sample_window
if sample_end>=len(data): sample_end = len(data)-1
data_window = data[sample_start:sample_end]
energy_freq = self._calculate_normalized_energy(data_window)
sum_voice_energy = self._sum_energy_in_band(energy_freq, start_band, end_band)
sum_full_energy = sum(energy_freq.values())
speech_ratio = sum_voice_energy/sum_full_energy
#self.speech_ratio2 = speech_ratio
# Hipothesis is that when there is a speech sequence we have ratio of energies more than Threshold
speech_ratio = speech_ratio>self.speech_energy_threshold
detected_windows = np.append(detected_windows,[sample_start, speech_ratio])
sample_start += sample_overlap
detected_windows = detected_windows.reshape(int(len(detected_windows)/2),2)
detected_windows[:,1] = self._smooth_speech_detection(detected_windows)
return detected_windows
def printing(self):
print(self.speech_ratio)
return self.speech_ratio
def\uuuu init\uuuuuuuuuuuuu（self，wave\u input\u文件名）：
self._read_wav（wave_input_filename）。_convert_to_mono（）
self.sample_window=0.02#20 ms
自采样重叠=0.01#10ms
self.speech_window=0.5#半秒
self.speech_energy_threshold=0.6#声带能量的60%
self.speech\u start\u波段=300
self.speech\u end\u波段=3000
#self.speech\u比率=0
def检测_语音（自我）：
“”“根据语音频带能量之间的比率检测语音区域。”
和总能量。
输出是窗口编号和语音标志的数组（1-语音，0-非语音）。
"""
检测到\u windows=np.array（[]）个
样本窗口=int（自率*自样本窗口）
样本重叠=int（自率*自样本重叠）
data=self.data
示例_start=0
开始\u波段=self.speech\u开始\u波段
end_波段=self.speech_end_波段
而（样本开始<（镜头（数据）-样本窗口））：
样本结束=样本开始+样本窗口
如果样本长度>=len（数据）：样本长度=len（数据）-1
数据窗口=数据[样本开始：样本结束]
能量\频率=自身。\计算\归一化\能量（数据窗口）
sum\u voice\u energy=self.\u sum\u energy\u在\u波段（energy\u freq、start\u波段、end\u波段）
sum\u full\u energy=sum（energy\u freq.values（））
语音比=总语音能量/总满能量
#self.speech\u ratio2=speech\u比率
#Hipothesis是指当存在语音序列时，我们的能量比超过阈值
语音比=语音比>自语音能量阈值
检测到的\u窗口=np.append（检测到的\u窗口，[示例\u开始，语音\u比率]）
样本\u开始+=样本\u重叠
检测到的窗口=检测到的窗口。重新整形（int（len（检测到的窗口）/2），2）
检测到的\u窗口[：，1]=自平滑\u语音\u检测（检测到的\u窗口）
返回检测到的窗口
def打印（自）：
打印（自述率）
返回自语言比
如果我没有在init函数中初始化speech\u ratio，它将根本不是我对象的属性。您可以使用
self.speech\u ratio