def prepare_training(self, file_id_list_name, wav_dir, lab_dir, mfc_dir, work_dir, multiple_speaker):
print('---preparing enverionment')
self.cfg_dir = os.path.join(work_dir, 'config')
self.model_dir = os.path.join(work_dir, 'model')
self.cur_dir = os.path.join(self.model_dir, 'hmm0')
if not os.path.exists(self.cfg_dir):
os.makedirs(self.cfg_dir)
if not os.path.exists(self.cur_dir):
os.makedirs(self.cur_dir)
self.phonemes = os.path.join(work_dir, 'mono_phone.list')
self.phoneme_map = os.path.join(work_dir, 'phoneme_map.dict')
# HMMs
self.proto = os.path.join(self.cfg_dir, 'proto')
# SCP files
self.copy_scp = os.path.join(self.cfg_dir, 'copy.scp')
self.test_scp = os.path.join(self.cfg_dir, 'test.scp')
self.train_scp = os.path.join(self.cfg_dir, 'train.scp')
# CFG
self.cfg = os.path.join(self.cfg_dir, 'cfg')
# The following is only correct for the default values in the cfg file given
# in gen_mfcc.py. If you changed the cfg for mfcc extraction, change it here accordingly.
open(self.cfg, 'w').write("""TARGETRATE = 50000.0
TARGETKIND = USER
WINDOWSIZE = 250000.0
PREEMCOEF = 0.97
USEHAMMING = T
ENORMALIZE = T
CEPLIFTER = 22
NUMCHANS = 20
NUMCEPS = 12
""")
self.wav_dir = wav_dir
self.lab_dir = lab_dir
self.mfc_dir = mfc_dir
if not os.path.exists(self.mfc_dir):
os.makedirs(self.mfc_dir)
self.mono_lab_dir = os.path.join(work_dir, 'mono_no_align')
if not os.path.exists(self.mono_lab_dir):
# shutil.rmtree(self.mono_lab_dir)
os.makedirs(self.mono_lab_dir)
file_id_list = self._read_file_list(file_id_list_name)
print('---checking data')
speaker_utt_dict = self._check_data(file_id_list, multiple_speaker)
print('---feature_normalisation')
for key_name in list(speaker_utt_dict.keys()):
print(" ---create normaliser for speaker {}.".format(key_name))
normaliser = MeanVarianceNorm(39)
normaliser.feature_normalisation(speaker_utt_dict[key_name], speaker_utt_dict[key_name]) ## save to itself
print(time.strftime("%c"))
print('---making proto')
self._make_proto()
def prepare_training(self, file_id_list_name, lab_dir, work_dir,
multiple_speaker):
print '---preparing enverionment'
self.cfg_dir = os.path.join(work_dir, 'config')
self.model_dir = os.path.join(work_dir, 'model')
self.cur_dir = os.path.join(self.model_dir, 'hmm0')
if not os.path.exists(self.cfg_dir):
os.makedirs(self.cfg_dir)
if not os.path.exists(self.cur_dir):
os.makedirs(self.cur_dir)
self.phonemes = os.path.join(work_dir, 'mono_phone.list')
self.phoneme_map = os.path.join(work_dir, 'phoneme_map.dict')
# HMMs
self.proto = os.path.join(self.cfg_dir, 'proto')
# SCP files
self.copy_scp = os.path.join(self.cfg_dir, 'copy.scp')
self.test_scp = os.path.join(self.cfg_dir, 'test.scp')
self.train_scp = os.path.join(self.cfg_dir, 'train.scp')
# CFG
self.cfg = os.path.join(self.cfg_dir, 'cfg')
self.wav_dir = wav_dir
self.lab_dir = lab_dir
self.mfc_dir = os.path.join(work_dir, 'mfc')
if not os.path.exists(self.mfc_dir):
os.makedirs(self.mfc_dir)
self.mono_lab_dir = os.path.join(work_dir, 'mono_no_align')
if not os.path.exists(self.mono_lab_dir):
os.makedirs(self.mono_lab_dir)
self.temp_path = os.path.join(work_dir, 'tmp')
if not os.path.exists(self.temp_path):
os.makedirs(self.temp_path)
self.scp_split_dir = os.path.join(self.temp_path, 'scp_split')
if not os.path.exists(self.scp_split_dir):
os.makedirs(self.scp_split_dir)
self.split_per_utterance = 1000
file_id_list = self._read_file_list(file_id_list_name)
print '---checking data'
speaker_utt_dict = self._check_data(file_id_list, multiple_speaker)
print '---extracting features'
self._HCopy()
print time.strftime("%c")
print '---feature_normalisation'
normaliser = MeanVarianceNorm(39)
for key_name in speaker_utt_dict.keys():
normaliser.feature_normalisation(
speaker_utt_dict[key_name],
speaker_utt_dict[key_name]) ## save to itself
print time.strftime("%c")
print '---making proto'
self._make_proto()
def prepare_training(self, file_id_list_name, wav_dir, lab_dir, work_dir,
multiple_speaker):
print('---preparing environment')
self.cfg_dir = os.path.join(work_dir, 'config')
self.model_dir = os.path.join(work_dir, 'model')
self.cur_dir = os.path.join(self.model_dir, 'hmm0')
if not os.path.exists(self.cfg_dir):
os.makedirs(self.cfg_dir)
if not os.path.exists(self.cur_dir):
os.makedirs(self.cur_dir)
self.phonemes = os.path.join(work_dir, 'mono_phone.list')
self.phoneme_map = os.path.join(work_dir, 'phoneme_map.dict')
# HMMs
self.proto = os.path.join(self.cfg_dir, 'proto')
# SCP files
self.copy_scp = os.path.join(self.cfg_dir, 'copy.scp')
self.test_scp = os.path.join(self.cfg_dir, 'test.scp')
self.train_scp = os.path.join(self.cfg_dir, 'train.scp')
# CFG
self.cfg = os.path.join(self.cfg_dir, 'cfg')
self.wav_dir = "/lium/raid01_b/tgranjon/synpaflex/wavs"
self.lab_dir = lab_dir
self.mfc_dir = os.path.join(work_dir, 'mfc')
if not os.path.exists(self.mfc_dir):
os.makedirs(self.mfc_dir)
self.mono_lab_dir = os.path.join(work_dir, 'mono_no_align')
if not os.path.exists(self.mono_lab_dir):
os.makedirs(self.mono_lab_dir)
file_id_list = self._read_file_list(file_id_list_name)
print('---checking data')
speaker_utt_dict = self._check_data(file_id_list, multiple_speaker)
print('---extracting features')
self._HCopy()
print(time.strftime("%c"))
print('---feature_normalisation')
for key_name in speaker_utt_dict.keys():
normaliser = MeanVarianceNorm(39)
normaliser.feature_normalisation(
speaker_utt_dict[key_name],
speaker_utt_dict[key_name]) ## save to itself
print(time.strftime("%c"))
print('---making proto')
self._make_proto()
def prepare_training(self, file_id_list_name, wav_dir, lab_dir, work_dir,
multiple_speaker):
print("---preparing enverionment")
self.cfg_dir = os.path.join(work_dir, "config")
self.model_dir = os.path.join(work_dir, "model")
self.cur_dir = os.path.join(self.model_dir, "hmm0")
if not os.path.exists(self.cfg_dir):
os.makedirs(self.cfg_dir)
if not os.path.exists(self.cur_dir):
os.makedirs(self.cur_dir)
self.phonemes = os.path.join(work_dir, "mono_phone.list")
self.phoneme_map = os.path.join(work_dir, "phoneme_map.dict")
# HMMs
self.proto = os.path.join(self.cfg_dir, "proto")
# SCP files
self.copy_scp = os.path.join(self.cfg_dir, "copy.scp")
self.test_scp = os.path.join(self.cfg_dir, "test.scp")
self.train_scp = os.path.join(self.cfg_dir, "train.scp")
# CFG
self.cfg = os.path.join(self.cfg_dir, "cfg")
self.wav_dir = wav_dir
self.lab_dir = lab_dir
self.mfc_dir = os.path.join(work_dir, "mfc")
if not os.path.exists(self.mfc_dir):
os.makedirs(self.mfc_dir)
self.mono_lab_dir = os.path.join(work_dir, "mono_no_align")
if not os.path.exists(self.mono_lab_dir):
os.makedirs(self.mono_lab_dir)
file_id_list = self._read_file_list(file_id_list_name)
print("---checking data")
speaker_utt_dict = self._check_data(file_id_list, multiple_speaker)
print("---extracting features")
self._HCopy()
print(time.strftime("%c"))
print("---feature_normalisation")
normaliser = MeanVarianceNorm(39)
for key_name in list(speaker_utt_dict.keys()):
normaliser.feature_normalisation(
speaker_utt_dict[key_name],
speaker_utt_dict[key_name]) ## save to itself
print(time.strftime("%c"))
print("---making proto")
self._make_proto()
def prepare_training(self, file_id_list_name, wav_dir, lab_dir, work_dir, multiple_speaker):
print('---preparing enverionment')
self.cfg_dir = os.path.join(work_dir, 'config')
self.model_dir = os.path.join(work_dir, 'model')
self.cur_dir = os.path.join(self.model_dir, 'hmm0')
if not os.path.exists(self.cfg_dir):
os.makedirs(self.cfg_dir)
if not os.path.exists(self.cur_dir):
os.makedirs(self.cur_dir)
self.phonemes = os.path.join(work_dir, 'mono_phone.list')
self.phoneme_map = os.path.join(work_dir, 'phoneme_map.dict')
# HMMs
self.proto = os.path.join(self.cfg_dir, 'proto')
# SCP files
self.copy_scp = os.path.join(self.cfg_dir, 'copy.scp')
self.test_scp = os.path.join(self.cfg_dir, 'test.scp')
self.train_scp = os.path.join(self.cfg_dir, 'train.scp')
# CFG
self.cfg = os.path.join(self.cfg_dir, 'cfg')
self.wav_dir=wav_dir
self.lab_dir = lab_dir
self.mfc_dir = os.path.join(work_dir, 'mfc')
if not os.path.exists(self.mfc_dir):
os.makedirs(self.mfc_dir)
self.mono_lab_dir = os.path.join(work_dir, 'mono_no_align')
if not os.path.exists(self.mono_lab_dir):
os.makedirs(self.mono_lab_dir)
file_id_list = self._read_file_list(file_id_list_name)
print('---checking data')
speaker_utt_dict = self._check_data(file_id_list, multiple_speaker)
print('---extracting features')
self._HCopy()
print(time.strftime("%c"))
print('---feature_normalisation')
normaliser = MeanVarianceNorm(39)
for key_name in list(speaker_utt_dict.keys()):
normaliser.feature_normalisation(speaker_utt_dict[key_name], speaker_utt_dict[key_name]) ## save to itself
print(time.strftime("%c"))
print('---making proto')
self._make_proto()