mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
* Init commit for recipes trained on multiple zh datasets. * fbank extraction for thchs30 * added support for aishell1 * added support for aishell-2 * fixes * fixes * fixes * added support for stcmds and primewords * fixes * added support for magicdata script for fbank computation not done yet * added script for magicdata fbank computation * file permission fixed * updated for the wenetspeech recipe * updated * Update preprocess_kespeech.py * updated * updated * updated * updated * file permission fixed * updated paths * fixes * added support for kespeech dev/test set fbank computation * fixes for file permission * refined support for KeSpeech * added scripts for BPE model training * updated * init commit for the multi_zh-cn zipformer recipe * disable speed perturbation by default * updated * updated * added necessary files for the zipformer recipe * removed redundant wenetspeech M and S sets * updates for multi dataset decoding * refined * formatting issues fixed * updated * minor fixes * this commit finalize the recipe (hopefully) * fixed formatting issues * minor fixes * updated * using soft links to reduce redundancy * minor updates * using soft links to reduce redundancy * minor updates * minor updates * using soft links to reduce redundancy * minor updates * Update README.md * minor updates * Update egs/multi_zh-hans/ASR/local/compute_fbank_magicdata.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_magicdata.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_stcmds.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_stcmds.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_primewords.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/compute_fbank_primewords.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * minor updates * minor fixes * fixed a formatting issue * Update preprocess_kespeech.py * Update prepare.sh * Update egs/multi_zh-hans/ASR/local/compute_fbank_kespeech_splits.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * Update egs/multi_zh-hans/ASR/local/preprocess_kespeech.py Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com> * removed redundant files * symlinks added * minor updates * added CI tests for `multi_zh-hans` * minor fixes * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh * Update run-multi-zh_hans-zipformer.sh --------- Co-authored-by: Fangjun Kuang <csukuangfj@gmail.com>
128 lines
4.1 KiB
Python
Executable File
128 lines
4.1 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
# Copyright 2023 Xiaomi Corp. (authors: Fangjun Kuang
|
|
# Zengrui Jin)
|
|
#
|
|
# 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.
|
|
|
|
|
|
"""
|
|
This file computes fbank features of the THCHS-30 dataset.
|
|
It looks for manifests in the directory data/manifests/thchs30.
|
|
|
|
The generated fbank features are saved in data/fbank.
|
|
"""
|
|
|
|
import argparse
|
|
import logging
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import torch
|
|
from lhotse import CutSet, Fbank, FbankConfig, LilcomChunkyWriter
|
|
from lhotse.recipes.utils import read_manifests_if_cached
|
|
|
|
from icefall.utils import get_executor
|
|
|
|
# Torch's multithreaded behavior needs to be disabled or
|
|
# it wastes a lot of CPU and slow things down.
|
|
# Do this outside of main() in case it needs to take effect
|
|
# even when we are not invoking the main (e.g. when spawning subprocesses).
|
|
torch.set_num_threads(1)
|
|
torch.set_num_interop_threads(1)
|
|
|
|
|
|
def compute_fbank_thchs30(num_mel_bins: int = 80, speed_perturb: bool = False):
|
|
src_dir = Path("data/manifests/thchs30")
|
|
output_dir = Path("data/fbank")
|
|
num_jobs = min(15, os.cpu_count())
|
|
|
|
dataset_parts = (
|
|
"train",
|
|
"dev",
|
|
"test",
|
|
)
|
|
prefix = "thchs_30"
|
|
suffix = "jsonl.gz"
|
|
manifests = read_manifests_if_cached(
|
|
dataset_parts=dataset_parts,
|
|
output_dir=src_dir,
|
|
prefix=prefix,
|
|
suffix=suffix,
|
|
)
|
|
assert manifests is not None
|
|
|
|
assert len(manifests) == len(dataset_parts), (
|
|
len(manifests),
|
|
len(dataset_parts),
|
|
list(manifests.keys()),
|
|
dataset_parts,
|
|
)
|
|
|
|
extractor = Fbank(FbankConfig(num_mel_bins=num_mel_bins))
|
|
|
|
with get_executor() as ex: # Initialize the executor only once.
|
|
for partition, m in manifests.items():
|
|
if (output_dir / f"{prefix}_cuts_{partition}.{suffix}").is_file():
|
|
logging.info(f"{partition} already exists - skipping.")
|
|
continue
|
|
logging.info(f"Processing {partition}")
|
|
cut_set = CutSet.from_manifests(
|
|
recordings=m["recordings"],
|
|
supervisions=m["supervisions"],
|
|
)
|
|
if "train" in partition:
|
|
cut_set = (
|
|
(cut_set + cut_set.perturb_speed(0.9) + cut_set.perturb_speed(1.1))
|
|
if speed_perturb
|
|
else cut_set
|
|
)
|
|
cut_set = cut_set.compute_and_store_features(
|
|
extractor=extractor,
|
|
storage_path=f"{output_dir}/{prefix}_feats_{partition}",
|
|
# when an executor is specified, make more partitions
|
|
num_jobs=num_jobs if ex is None else 80,
|
|
executor=ex,
|
|
storage_type=LilcomChunkyWriter,
|
|
)
|
|
cut_set.to_file(output_dir / f"{prefix}_cuts_{partition}.{suffix}")
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument(
|
|
"--num-mel-bins",
|
|
type=int,
|
|
default=80,
|
|
help="""The number of mel bins for Fbank""",
|
|
)
|
|
parser.add_argument(
|
|
"--speed-perturb",
|
|
type=bool,
|
|
default=False,
|
|
help="Enable 0.9 and 1.1 speed perturbation for data augmentation. Default: False.",
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
formatter = "%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"
|
|
|
|
logging.basicConfig(format=formatter, level=logging.INFO)
|
|
|
|
args = get_args()
|
|
compute_fbank_thchs30(
|
|
num_mel_bins=args.num_mel_bins, speed_perturb=args.speed_perturb
|
|
)
|