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 compute_statistics for coqpit

This commit is contained in:
Eren Gölge 2021-05-03 16:39:55 +02:00
parent 79d7215142
commit c34c8137d7
1 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
TTS/bin/compute_statistics.py
View File

@ -10,19 +10,22 @@ from tqdm import tqdm
from TTS.tts.datasets.preprocess import load_meta_data
from TTS.utils.audio import AudioProcessor
from TTS.utils.io import load_config
# from TTS.utils.io import load_config
from TTS.utils.config import load_config
def main():
"""Run preprocessing process."""
parser = argparse.ArgumentParser(
description="Compute mean and variance of spectrogtram features.")
parser.add_argument("config_path", type=str,
help="TTS config file path to define audio processin parameters.")
parser.add_argument("out_path", type=str,
help="save path (directory and filename).")
parser.add_argument("--data_path", type=str, required=False,
help="folder including the target set of wavs overriding dataset config.")
parser = argparse.ArgumentParser(description="Compute mean and variance of spectrogtram features.")
parser.add_argument("config_path", type=str, help="TTS config file path to define audio processin parameters.")
parser.add_argument("out_path", type=str, help="save path (directory and filename).")
parser.add_argument(
"--data_path",
type=str,
required=False,
help="folder including the target set of wavs overriding dataset config.",
)
args, overrides = parser.parse_known_args()
CONFIG = load_config(args.config_path)
@ -37,7 +40,7 @@ def main():
# load the meta data of target dataset
if args.data_path:
dataset_items = glob.glob(os.path.join(args.data_path, '**', '*.wav'), recursive=True)
dataset_items = glob.glob(os.path.join(args.data_path, "**", "*.wav"), recursive=True)
else:
dataset_items = load_meta_data(CONFIG.dataset_config)[0] # take only train data
print(f" > There are {len(dataset_items)} files.")
@ -85,7 +88,7 @@ def main():
del CONFIG.audio.min_level_db
del CONFIG.audio.symmetric_norm
del CONFIG.audio.clip_norm
stats['audio_config'] = CONFIG.audio.to_dict()
stats["audio_config"] = CONFIG.audio.to_dict()
np.save(output_file_path, stats, allow_pickle=True)
print(f" > stats saved to {output_file_path}")