def task_predict(input_file, input_model):
# FS = 8000
m = ModelInterface.load(input_model)
fs_noise, noise = read_wav("noise.wav")
m.init_noise(fs_noise, noise)
#for f in [input_files]:
try:
fs, signal = read_wav(input_file)
print("freq " + str(fs))
signal = m.filter(fs, signal)
print("len " + str(len(signal)))
if len(signal) < 50:
return None
print("AA")
label = m.predict(fs, signal)
print input_file, '->', label
return label
except:
print "Unexpected error:", sys.exc_info()[0]
def task_enroll(input_directory, output_model):
m = ModelInterface()
for k in input_directory.strip().split():
input_dirs = [os.path.expanduser(k)]
for d in input_directory:
dirs = itertools.chain(*(glob.glob(d)))
for d in dirs:
if os.path.isdir(d):
dirs = [d]
files = []
if len(dirs) == 0:
print "No valid directory found!"
sys.exit(1)
for d in dirs:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print "No wav file found in {0}".format(d)
continue
print "Label {0} has files {1}".format(label, ','.join(wavs))
for wav in wavs:
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
m.train()
m.dump(output_model)
def task_enroll(input_dirs, output_model):
m = ModelInterface()
input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()]
dirs = itertools.chain(*(glob.glob(d) for d in input_dirs))
dirs = [d for d in dirs if os.path.isdir(d)]
files = []
if len(dirs) == 0:
print ("No valid directory found!")
sys.exit(1)
for d in dirs:
label = os.path.basename(d.rstrip('/'))
#label =d
wavs = glob.glob(d + '/*.wav')
#print(wavs)
if len(wavs) == 0:
print ("No wav file found in {0}".format(d))
continue
print ("Label {0} has files {1}".format(label, ','.join(wavs)))
for wav in wavs:
fs, signal = read_wav(wav)
label=wav.split('/')[-1].split('_')[0]
#print(label)
m.enroll(label, fs, signal)
m.train()
m.dump(output_model)
def task_enroll(input_dirs, output_model):
m = ModelInterface()
input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()]
dirs = itertools.chain(*(glob.glob(d) for d in input_dirs))
dirs = [d for d in dirs if os.path.isdir(d)]
files = []
if len(dirs) == 0:
print "No valid directory found!"
sys.exit(1)
training_stats = []
for d in dirs:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print "No wav file found in {0}".format(d)
continue
print "Label '{0}' has files: {1}".format(label, ', '.join(wavs))
total_len = 0
for wav in wavs:
fs, signal = read_wav(wav)
print " File '{}' has frequency={} and length={}".format(
wav, fs, len(signal))
total_len += len(signal)
m.enroll(label, fs, signal)
training_stats.append((label, total_len))
print "--------------------------------------------"
for label, total_len in training_stats:
print "Total length of training data for '{}' is {}".format(
label, total_len)
print "For best accuracy, please make sure all labels have similar amount of training data!"
m.train()
m.dump(output_model)
def task_enroll(input_dirs, output_model):
m = ModelInterface()
input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()]
dirs = itertools.chain(*(glob.glob(d) for d in input_dirs))
dirs = [d for d in dirs if os.path.isdir(d)]
files = []
if len(dirs) == 0:
print "No valid directory found!"
sys.exit(1)
training_stats = []
for d in dirs:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print "No wav file found in {0}".format(d)
continue
print "Label '{0}' has files: {1}".format(label, ', '.join(wavs))
total_len = 0
for wav in wavs:
fs, signal = read_wav(wav)
print " File '{}' has frequency={} and length={}".format(wav, fs, len(signal))
total_len += len(signal)
m.enroll(label, fs, signal)
training_stats.append((label, total_len))
print "--------------------------------------------"
for label, total_len in training_stats:
print "Total length of training data for '{}' is {}".format(label, total_len)
print "For best accuracy, please make sure all labels have similar amount of training data!"
m.train()
m.dump(output_model)
def task_predict(input_files, input_model):
m = ModelInterface.load(input_model)
for f in glob.glob(os.path.expanduser(input_files)):
fs, signal = read_wav(f)
label = m.predict(fs, signal)
f = os.path.basename(f)
print f, '->', label
def task_predict(input_files, input_model):
m = ModelInterface.load(input_model)
for f in glob.glob(os.path.expanduser(input_files)):
wavs = glob.glob(f + '/*.wav')
for wav in wavs:
fs, signal = read_wav(wav)
label = m.predict(fs, signal)
print (wav.split('/')[-1].split('_')[0]+'|->|'+label)
def task_predict(input_model):
m = ModelInterface.load(input_model)
test_data = range(1, 4)
for f in test_data:
wav = "./data/test/" + str(f) + ".wav"
print wav
fs, signal = read_wav(wav)
label = m.predict(fs, signal)
print f, '->', label
def task_predict(input_model):
m = ModelInterface.load(input_model)
test_data = range(1,4)
for f in test_data:
wav = "./data/test/"+str(f)+".wav"
print wav
fs, signal = read_wav(wav)
label = m.predict(fs, signal)
print f, '->', label
def reco_files(self):
fnames = QFileDialog.getOpenFileNames(self, "Select Wav Files", "",
"Files (*.wav)")
print('reco_files')
for f in fnames:
fs, sig = read_wav(f)
newsig = self.backend.filter(fs, sig)
label = self.backend.predict(fs, newsig)
print(f, label)
def task_predict(input_files, input_model, index):
m = ModelInterface.load(input_model)
for f in glob.glob(os.path.expanduser(input_files)):
fs, signal = read_wav(f)
label = m.predict(fs, signal)
print f, '->', label
if label == index:
sys.exit(1)
else:
sys.exit(2)
def enroll_file(self):
fname = QFileDialog.getOpenFileName(self, "Open Wav File", "",
"Files (*.wav)")
if not fname:
return
self.status(fname)
self.enrollFileName.setText(fname)
fs, signal = read_wav(fname)
signal = monophonic(signal)
self.enrollWav = (fs, signal)
def reco_file(self):
fname = QFileDialog.getOpenFileName(self, "Open Wav File", "",
"Files (*.wav)")
print('reco_file')
if not fname:
return
self.status(fname)
fs, signal = read_wav(fname)
self.reco_do_predict(fs, signal)
def task_predict(input_files, input_model):
m = ModelInterface.load(input_model)
for f in glob.glob(os.path.expanduser(input_files)):
fs, signal = read_wav(f)
#label = m.predict(fs, signal)
(label, score) = m.predict_with_score(fs, signal)
if math.fabs(score) < 0.13:
print f, '->', label, ' score:', score
else:
print f, 'NO SPEAKER RECOGNIZED (', label, ' score:', score, ')'
def task_enroll(output_model):
m = ModelInterface()
train_data = range(1,4)
for i in train_data:
wav = "./data/train/"+str(i)+".wav"
print wav
label = str(i)
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
m.train()
m.dump(output_model)
def task_enroll(output_model):
m = ModelInterface()
train_data = range(1, 4)
for i in train_data:
wav = "./data/train/" + str(i) + ".wav"
print wav
label = str(i)
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
m.train()
m.dump(output_model)
def handle_speaker_rec_greeting_intent(self, message):
directory = "/tmp/mycroft_wake_words"
self.newest = max(glob.iglob(os.path.join(directory, '*.wav')),
key=os.path.getctime)
CWD_PATH = os.path.dirname(__file__)
input_model = os.path.join(CWD_PATH, "model.out")
m = ModelInterface.load(input_model)
input_files = self.newest
fs, signal = read_wav(input_files)
label = m.predict(fs, signal)
self.speak("Yes, I do recognize your voice, %s" % (label))
print(self.newest)
def task_predict(input_files, input_model):
m = ModelInterface.load(input_model)
ev = []
for f in glob.glob(os.path.expanduser(input_files)):
fs, signal = read_wav(f)
label = m.predict(fs, signal)
ev.append(label)
print f, '->', label
size = len(ev)
cnt = Counter(ev)
mostCommon = cnt.most_common(1)[0][1]
print(mostCommon)
print(mostCommon * 100 / size)
def task_predict(input_files, input_current, input_model):
m = ModelInterface.load(input_model)
with open('/host{0}/predictions.csv'.format(input_current), 'w') as pred:
ss = csv.writer(pred, delimiter=',')
ss.writerow(['score', 'label', 'file'])
for f in glob.glob(os.path.expanduser(input_files)):
fs, signal = read_wav(f)
scores = m.predict_scores(fs, signal)
y_scores = dict(zip(m.gmmset.y, scores))
i = 0
for label, score in sorted(y_scores.items(),
key=lambda o: o[1],
reverse=True):
if i == 0 and label in [
'Albert', 'Casado', 'Pedro', 'Iglesias'
]:
ss.writerow([score, label, f])
i += 1
def do_enroll(self):
name = self.Username.text()
if not name:
self.warn("Please Input Your Name")
return
# self.addUserInfo()
# new_signal = self.backend.filter(*self.enrollWav)
# print ("After removed: {0} -> {1}".format(len(self.enrollWav[1]), len(new_signal)))
# print ("Enroll: {:.4f} seconds".format(float(len(new_signal)) / Main.FS))
# if len(new_signal) == 0:
# print( "Error! Input is silent! Please enroll again")
# return
path = 'suara/' + str(name) + '/'
wavs = glob.glob(path + '*.wav')
for wav in wavs:
fs, signal = read_wav(wav)
new_signal = self.backend.filter(fs, signal)
self.backend.enroll(name, fs, new_signal)
def task_enroll(input_dirs, output_model):
m = ModelInterface()
input_dirs = [os.path.expanduser(k) for k in input_dirs.strip().split()]
dirs = itertools.chain(*(glob.glob(d) for d in input_dirs))
dirs = [d for d in dirs if os.path.isdir(d)]
files = []
if len(dirs) == 0:
print "No valid directory found!"
sys.exit(1)
for d in dirs:
label = os.path.basename(d.rstrip('/'))
wavs = glob.glob(d + '/*.wav')
if len(wavs) == 0:
print "No wav file found in {0}".format(d)
continue
print "Label {0} has files {1}".format(label, ','.join(wavs))
for wav in wavs:
fs, signal = read_wav(wav)
m.enroll(label, fs, signal)
m.train()
m.dump(output_model)
fs, signal = read_wav(input_file)
print("freq " + str(fs))
signal = m.filter(fs, signal)
print("len " + str(len(signal)))
if len(signal) < 50:
return None
print("AA")
label = m.predict(fs, signal)
print input_file, '->', label
return label
except:
print "Unexpected error:", sys.exc_info()[0]
m = None
if __name__ == '__main__':
global args
args = get_args()
fs_noise, noise = read_wav("noise.wav")
m_enroll.init_noise(fs_noise, noise)
task = args.task
if task == 'enroll':
task_enroll(args.input, args.model)
elif task == 'predict':
task_predict(args.input, args.model)
def __init__(self, parent=None):
QWidget.__init__(self, parent)
uic.loadUi("gui/edytor.ui", self)
self.last_none_start = 0
self.last_switch_user = 0
self.last_enter_none_handler = False
self.last_user_detected = 'None'
self.statusBar()
self.check_result = False
self.timer = QTimer(self)
self.timer.timeout.connect(self.timer_callback)
self.noiseButton.clicked.connect(self.noise_clicked)
self.recording_noise = False
self.loadNoise.clicked.connect(self.load_noise)
self.AddUser.clicked.connect(self.add_user)
self.enrollRecord.clicked.connect(self.start_enroll_record)
self.stopEnrollRecord.clicked.connect(self.stop_enroll_record)
self.enrollFile.clicked.connect(self.enroll_file)
self.enroll.clicked.connect(self.do_enroll)
self.startTrain.clicked.connect(self.start_train)
self.dumpBtn.clicked.connect(self.dump)
self.loadBtn.clicked.connect(self.load)
self.recoRecord.clicked.connect(self.start_reco_record)
self.stopRecoRecord.clicked.connect(self.stop_reco_record)
# self.newReco.clicked.connect(self.new_reco)
self.recoFile.clicked.connect(self.reco_file)
self.recoInputFiles.clicked.connect(self.reco_files)
#UI.init
self.userdata = []
self.loadUsers()
self.Userchooser.currentIndexChanged.connect(self.showUserInfo)
self.ClearInfo.clicked.connect(self.clearUserInfo)
self.UpdateInfo.clicked.connect(self.updateUserInfo)
self.UploadImage.clicked.connect(self.upload_avatar)
#movie test
self.movie = QMovie(u"gui/image/recording.gif")
self.movie.start()
self.movie.stop()
self.Animation.setMovie(self.movie)
self.Animation_2.setMovie(self.movie)
self.Animation_3.setMovie(self.movie)
self.aladingpic = QPixmap(u"gui/image/a_hello.png")
self.Alading.setPixmap(self.aladingpic)
self.Alading_conv.setPixmap(self.aladingpic)
#default user image setting
self.avatarname = "gui/image/nouser.jpg"
self.defaultimage = QPixmap(self.avatarname)
self.Userimage.setPixmap(self.defaultimage)
self.recoUserImage.setPixmap(self.defaultimage)
self.convUserImage.setPixmap(self.defaultimage)
self.load_avatar('gui/avatar/')
#quick enroll
self.show_checkbox()
self.checkbox.setWidget(self.available_to_enroll)
self.LoadAll.clicked.connect(self.enroll_checklist)
#Conversation Mode Variables
self.conv_record = np.array([], dtype=NPDtype)
self.time_init = QTimer(self)
self.current_label = None
# Graph Window init
self.graphwindow = GraphWindow()
self.newname = ""
self.lastname = ""
self.Graph_button.clicked.connect(self.graphwindow.show)
self.convRecord.clicked.connect(self.start_conv_record)
self.convStop.clicked.connect(self.stop_conv)
self.generateTranscript.clicked.connect(self.generate_transcript)
self.backend = ModelInterface()
# debug
QShortcut(QKeySequence("Ctrl+P"), self, self.printDebug)
#init
try:
fs, signal = read_wav("bg.wav")
self.backend.init_noise(fs, signal)
except:
pass
def load_noise(self):
fname = QFileDialog.getOpenFileName(self, "Open Data File:", "",
"Wav File (*.wav)")
if fname:
fs, signal = read_wav(fname)
self.backend.init_noise(fs, signal)