mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 17:42:21 +00:00
d67a49afe4
* Add Common Voice for multidataset * Add prepare_multidataset.sh * Add dataset mixing * Update prepare_multidataset.sh * Update prepare_giga_speech.sh * update comments * Add split and shuffle mechanism * Add multi-dataset train * Fix for deleting * Fix for modifying * Add comments * Change type for perturb_speed * Fix for style check * Small fix * Add filter * Remove warning
54 lines
1.8 KiB
Python
54 lines
1.8 KiB
Python
# Copyright 2023 Xiaomi Corp. (authors: Yifan Yang)
|
|
#
|
|
# See ../../../../LICENSE for clarification regarding multiple authors
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
|
|
import glob
|
|
import logging
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import lhotse
|
|
from lhotse import CutSet, load_manifest_lazy
|
|
|
|
|
|
class MultiDataset:
|
|
def __init__(self, manifest_dir: str):
|
|
"""
|
|
Args:
|
|
manifest_dir:
|
|
It is expected to contain the following files:
|
|
|
|
- multidataset_split_1998/multidataset/multidataset_cuts_train.*.jsonl.gz
|
|
"""
|
|
self.manifest_dir = Path(manifest_dir)
|
|
|
|
def train_cuts(self) -> CutSet:
|
|
logging.info("About to get multidataset train cuts")
|
|
|
|
filenames = glob.glob(
|
|
f"{self.manifest_dir}/multidataset_split_1998/multidataset/multidataset_cuts_train.*.jsonl.gz"
|
|
)
|
|
|
|
pattern = re.compile(r"multidataset_cuts_train.([0-9]+).jsonl.gz")
|
|
idx_filenames = ((int(pattern.search(f).group(1)), f) for f in filenames)
|
|
idx_filenames = sorted(idx_filenames, key=lambda x: x[0])
|
|
|
|
sorted_filenames = [f[1] for f in idx_filenames]
|
|
|
|
logging.info(f"Loading {len(sorted_filenames)} splits")
|
|
|
|
return lhotse.combine(lhotse.load_manifest_lazy(p) for p in sorted_filenames)
|