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.
PaddleSpeech/data_utils/utility.py

36 lines
1.2 KiB

"""Contains data helper functions."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import json
import codecs
def read_manifest(manifest_path, max_duration=float('inf'), min_duration=0.0):
"""Load and parse manifest file.
Instances with durations outside [min_duration, max_duration] will be
filtered out.
:param manifest_path: Manifest file to load and parse.
:type manifest_path: basestring
:param max_duration: Maximal duration in seconds for instance filter.
:type max_duration: float
:param min_duration: Minimal duration in seconds for instance filter.
:type min_duration: float
:return: Manifest parsing results. List of dict.
:rtype: list
:raises IOError: If failed to parse the manifest.
"""
manifest = []
for json_line in codecs.open(manifest_path, 'r', 'utf-8'):
try:
json_data = json.loads(json_line)
except Exception as e:
raise IOError("Error reading manifest: %s" % str(e))
if (json_data["duration"] <= max_duration and
json_data["duration"] >= min_duration):
manifest.append(json_data)
return manifest