def samplePlot(fList):
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.ticker import NullFormatter # useful for `logit` scale
# Fixing random state for reproducibility
# plot with various axes scales
plt.figure(1)
i = 0
for file in fList:
i += 1
print(file)
plt.subplot(330 + i)
signal = rd.importSignal(file)
plotEach(signal)
# Format the minor tick labels of the y-axis into empty strings with
# `NullFormatter`, to avoid cumbering the axis with too many labels.
plt.gca().yaxis.set_minor_formatter(NullFormatter())
# Adjust the subplot layout, because the logit one may take more space
# than usual, due to y-tick labels like "1 - 10^{-3}"
plt.subplots_adjust(top=0.92,
bottom=0.08,
left=0.10,
right=0.95,
hspace=0.25,
wspace=0.35)
plt.show()
def execute(silences,
inputFolder='./raw/',
outputFolder='./train/',
segment=500,
verbose=True,
defaultSilenceLen=defaultLen):
import random as ran
silences_list_len = len(silences) # number of silences sample
for file in listFile(os.walk(inputFolder), ['*.wav']):
org = rd.importSignal(inputFolder + file)
wav, __len = trim(org, outOrgLen=True)
for i in range(
1
): # range (max ((defaultSilenceLen - __len) // segment-2, 1)):
idx = ran.randrange(0, silences_list_len)
choice = silences[idx]
seg = mix(wav, choice, i * segment)
sname = outputFolder + 'mix_%d_%d_%s' % (idx, i, file)
rd.save(seg, sname)
if verbose:
print("Saved file:%-40s with sample size:%5d" %
(sname, len(seg)))
def loadSilences(dir='./raw/silent/'):
silences = []
for silent in listFile(os.walk(dir), ['*.wav']):
silence = rd.importSignal('%s%s' % (dir, silent))[0:defaultLen]
silences.append(silence)
# print (len (silence))
return silences
def pretest():
wav1 = rd.importSignal('./raw/silent/silent0.wav')[0:defaultLen]
wav2, __len = trim(rd.importSignal('./raw/như/nhu1.wav'), outOrgLen=True)
wav = mix(wav2, wav1, 0)
fig = plt.gcf()
i = 0
seg = 1000
count = (len(wav1) - __len) // seg
print(count)
while 1:
i = (i + 1) % count
plt.clf()
wav = mix(wav2, wav1, i * seg)
plt.plot(wav)
fig.canvas.draw()
plt.pause(0.6)
def fimport(i, label):
mfcc = transRaw(rd.importSignal(folder + i), trim=True)
# mfcc = mfcc.reshape (defaultLen // particle, particle)
# wav = processWave (rd.importSignal (folder+i))
# sd.play (wav)
# sd.wait ()
# vz.plot (wav)
# vz.show ()
X_train.append(mfcc)
Y_train.append(label)
def check(i):
from time import time
wav = rd.importSignal(i)
mfcc = transRaw(wav, trim=True) # have to trim a word
#from time import sleep
mfcc = mfcc.reshape(1, mfcc.shape[0], mfcc.shape[1])
# mfcc = mfcc.reshape (1, defaultLen // particle, particle)
mark = time()
pred = lobe.predict(mfcc)
print('%-40s' % str(pred),
'for %10s estimate time in second: %5.4f' % (i, time() - mark),
end=' ')
chosen = 0
mx = 0
for i in range(len(pred[0])):
if mx < pred[0][i]:
chosen = i
mx = pred[0][i]
print('label:', chosen)
return (pred[0][0] >= 0.5)
def test():
file = 'tmp.wav'
signal = rd.importSignal(file)
print(signal)
print(type(signal))
rd.plot(signal, file)
def loadMfccFromFile(name):
wav = rd.importSignal(name)
return getMfcc(wav)