def ljspeech(path, hp):
csv_file = get_files(path, extension='.csv')
assert len(csv_file) == 1
wavs = []
#texts = []
#encode = []
with open(csv_file[0], encoding='utf-8') as f_:
# if 'phoneme_cleaners' in hp.tts_cleaner_names:
# print("Cleaner : {} Language Code : {}\n".format(hp.tts_cleaner_names[0],hp.phoneme_language))
# for line in f :
# split = line.split('|')
# text_dict[split[0]] = text2phone(split[-1].strip(),hp.phoneme_language)
# else:
print("Cleaner : {} \n".format(hp.tts_cleaner_names))
for line in f_:
sub = {}
split = line.split('|')
t = split[-1].strip().upper()
# t = t.replace('"', '')
# t = t.replace('-', ' ')
# t = t.replace(';','')
# t = t.replace('(', '')
# t = t.replace(')', '')
# t = t.replace(':', '')
# t = re.sub('[^A-Za-z0-9.!?,\' ]+', '', t)
if len(t) > 0:
wavs.append(split[0].strip())
#texts.append(t)
#encode.append(text_to_sequence(t, hp.tts_cleaner_names))
# with open(os.path.join(data_dir, 'train.txt'), 'w', encoding='utf-8') as f:
# for w, t, e in zip(wavs, texts, encode):
# f.write('{}|{}|{}'.format(w,e,t) + '\n')
return wavs #, texts, encode
if __name__ == "__main__":
hp = HParam("./configs/default.yaml")
min_e = []
min_p = []
max_e = []
max_p = []
nz_min_p = []
nz_min_e = []
energy_path = os.path.join(hp.data.data_dir, "energy")
pitch_path = os.path.join(hp.data.data_dir, "pitch")
mel_path = os.path.join(hp.data.data_dir, "mels")
energy_files = get_files(energy_path, extension=".npy")
pitch_files = get_files(pitch_path, extension=".npy")
mel_files = get_files(mel_path, extension=".npy")
assert len(energy_files) == len(pitch_files) == len(mel_files)
energy_vecs = []
for f in tqdm(energy_files):
e = np.load(f)
e = remove_outlier(e)
energy_vecs.append(e)
min_e.append(e.min())
nz_min_e.append(e[e > 0].min())
max_e.append(e.max())
nonzeros = np.concatenate([v[np.where(v != 0.0)[0]] for v in energy_vecs])
if __name__ == '__main__':
hp = HParam('./configs/default.yaml')
min_e = []
min_p = []
max_e = []
max_p = []
nz_min_p = []
nz_min_e = []
energy_path = os.path.join(hp.data.data_dir, 'energy')
pitch_path = os.path.join(hp.data.data_dir, 'pitch')
mel_path = os.path.join(hp.data.data_dir, 'mels')
energy_files = get_files(energy_path, extension='.npy')
pitch_files = get_files(pitch_path, extension='.npy')
mel_files = get_files(mel_path, extension='.npy')
assert len(energy_files) == len(pitch_files) == len(mel_files)
energy_vecs = []
for f in tqdm(energy_files):
e = np.load(f)
e = remove_outlier(e)
energy_vecs.append(e)
min_e.append(e.min())
nz_min_e.append(e[e > 0].min())
max_e.append(e.max())
nonzeros = np.concatenate([v[np.where(v != 0.0)[0]] for v in energy_vecs])