You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
57 lines
1.7 KiB
57 lines
1.7 KiB
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import argparse
|
|
from data_utils.normalizer import FeatureNormalizer
|
|
from data_utils.augmentor.augmentation import AugmentationPipeline
|
|
from data_utils.featurizer.audio_featurizer import AudioFeaturizer
|
|
|
|
parser = argparse.ArgumentParser(
|
|
description='Computing mean and stddev for feature normalizer.')
|
|
parser.add_argument(
|
|
"--manifest_path",
|
|
default='datasets/manifest.train',
|
|
type=str,
|
|
help="Manifest path for computing normalizer's mean and stddev."
|
|
"(default: %(default)s)")
|
|
parser.add_argument(
|
|
"--num_samples",
|
|
default=500,
|
|
type=int,
|
|
help="Number of samples for computing mean and stddev. "
|
|
"(default: %(default)s)")
|
|
parser.add_argument(
|
|
"--augmentation_config",
|
|
default='{}',
|
|
type=str,
|
|
help="Augmentation configuration in json-format. "
|
|
"(default: %(default)s)")
|
|
parser.add_argument(
|
|
"--output_file",
|
|
default='mean_std.npz',
|
|
type=str,
|
|
help="Filepath to write mean and std to (.npz)."
|
|
"(default: %(default)s)")
|
|
args = parser.parse_args()
|
|
|
|
|
|
def main():
|
|
augmentation_pipeline = AugmentationPipeline(args.augmentation_config)
|
|
audio_featurizer = AudioFeaturizer()
|
|
|
|
def augment_and_featurize(audio_segment):
|
|
augmentation_pipeline.transform_audio(audio_segment)
|
|
return audio_featurizer.featurize(audio_segment)
|
|
|
|
normalizer = FeatureNormalizer(
|
|
mean_std_filepath=None,
|
|
manifest_path=args.manifest_path,
|
|
featurize_func=augment_and_featurize,
|
|
num_samples=args.num_samples)
|
|
normalizer.write_to_file(args.output_file)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|