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/utils.py

20 lines
627 B

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import json
def read_manifest(manifest_path, max_duration=float('inf'), min_duration=0.0):
"""Load and parse manifest file."""
manifest = []
for json_line in open(manifest_path):
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