def compute_mean_std(manifest_path, num_samples, output_path):
normalizer = FeatureNormalizer(mean_std_filepath=None,
manifest_path=manifest_path,
num_samples=num_samples)
# 将计算的结果保存的文件中
normalizer.write_to_file(output_path)
print('计算的均值和标准值已保存在 %s！' % output_path)
def compute_mean_std(manifest_path, num_samples, output_path):
# 随机取指定的数量计算平均值归一化
normalizer = FeatureNormalizer(mean_std_filepath=None,
manifest_path=manifest_path,
num_samples=num_samples,
num_workers=args.num_workers)
# 将计算的结果保存的文件中
normalizer.write_to_file(output_path)
print('计算的均值和标准值已保存在 %s！' % output_path)
def main():
print_arguments(args)
audio_featurizer = AudioFeaturizer(specgram_type=args.specgram_type)
def augment_and_featurize(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_path)
def main():
print_arguments(args)
augmentation_pipeline = AugmentationPipeline('{}')
audio_featurizer = AudioFeaturizer(specgram_type=args.specgram_type)
def augment_and_featurize(audio_segment):
augmentation_pipeline.transform_audio(audio_segment)
return audio_featurizer.featurize(audio_segment)
# 随机取指定的数量计算平均值归一化
normalizer = FeatureNormalizer(mean_std_filepath=None,
manifest_path=args.manifest_path,
featurize_func=augment_and_featurize,
num_samples=args.num_samples)
# 将计算的结果保存的文件中
normalizer.write_to_file(args.output_path)