Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update extract_features.py and the order of columns in generated dataset file

This commit is contained in:
Eren Golge 2018-12-17 16:34:24 +01:00
parent 4587c72a03
commit b42e3d12a8
1 changed files with 4 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
extract_features.py
View File

@ -18,9 +18,7 @@ from multiprocessing import Pool
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--data_path', type=str, help='Data folder.')
parser.add_argument('--cache_path', type=str, help='Cache folder, place to output all the intermediate spectrogram files.')
# parser.add_argument('--keep_cache', type=bool, help='If True, it keeps the cache folder.')
# parser.add_argument('--hdf5_path', type=str, help='hdf5 folder.')
parser.add_argument('--cache_path', type=str, help='Cache folder, place to output all the spectrogram files.')
parser.add_argument(
'--config', type=str, help='conf.json file for run settings.')
parser.add_argument(
@ -49,24 +47,14 @@ if __name__ == "__main__":
print(" > Input path: ", DATA_PATH)
print(" > Cache path: ", CACHE_PATH)
# audio = importlib.import_module('utils.' + c.audio_processor)
# AudioProcessor = getattr(audio, 'AudioProcessor')
ap = AudioProcessor(**CONFIG.audio)
def trim_silence(self, wav):
""" Trim silent parts with a threshold and 0.1 sec margin """
margin = int(ap.sample_rate * 0.1)
wav = wav[margin:-margin]
return librosa.effects.trim(
wav, top_db=40, frame_length=1024, hop_length=256)[0]
def extract_mel(item):
""" Compute spectrograms, length information """
text = item[0]
file_path = item[1]
x = ap.load_wav(file_path, ap.sample_rate)
if args.trim_silence:
x = trim_silence(x)
file_name = os.path.basename(file_path).replace(".wav", "")
mel_file = file_name + "_mel"
mel_path = os.path.join(CACHE_PATH, 'mel', mel_file)
@ -74,20 +62,20 @@ if __name__ == "__main__":
np.save(mel_path, mel, allow_pickle=False)
mel_len = mel.shape[1]
wav_len = x.shape[0]
output = [file_path, mel_path+".npy", str(wav_len), str(mel_len), text]
output = [text, file_path, mel_path+".npy", str(wav_len), str(mel_len)]
if not args.only_mel:
linear_file = file_name + "_linear"
linear_path = os.path.join(CACHE_PATH, 'linear', linear_file)
linear = ap.spectrogram(x.astype('float32')).astype('float32')
linear_len = linear.shape[1]
np.save(linear_path, linear, allow_pickle=False)
output.insert(2, linear_path+".npy")
output.insert(3, linear_path+".npy")
if args.process_audio:
audio_file = file_name + "_audio"
audio_path = os.path.join(CACHE_PATH, 'audio', audio_file)
np.save(audio_path, x, allow_pickle=False)
del output[0]
output.insert(0, audio_path+".npy")
output.insert(1, audio_path+".npy")
assert mel_len == linear_len
return output