mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
f1abce72f8
* Use jsonl for cutsets in the librispeech recipe. * Use lazy cutset for all recipes. * More fixes to use lazy CutSet. * Remove force=True from logging to support Python < 3.8 * Minor fixes. * Fix style issues.
90 lines
2.7 KiB
Python
Executable File
90 lines
2.7 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
"""
|
|
This file computes fbank features of the yesno dataset.
|
|
It looks for manifests in the directory data/manifests.
|
|
|
|
The generated fbank features are saved in data/fbank.
|
|
"""
|
|
|
|
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_yesno():
|
|
src_dir = Path("data/manifests")
|
|
output_dir = Path("data/fbank")
|
|
|
|
# This dataset is rather small, so we use only one job
|
|
num_jobs = min(1, os.cpu_count())
|
|
num_mel_bins = 23
|
|
|
|
dataset_parts = (
|
|
"train",
|
|
"test",
|
|
)
|
|
prefix = "yesno"
|
|
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
|
|
|
|
extractor = Fbank(
|
|
FbankConfig(sampling_rate=8000, num_mel_bins=num_mel_bins)
|
|
)
|
|
|
|
with get_executor() as ex: # Initialize the executor only once.
|
|
for partition, m in manifests.items():
|
|
cuts_file = output_dir / f"{prefix}_cuts_{partition}.{suffix}"
|
|
if cuts_file.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)
|
|
)
|
|
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 1, # use one job
|
|
executor=ex,
|
|
storage_type=LilcomChunkyWriter,
|
|
)
|
|
cut_set.to_file(cuts_file)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
formatter = (
|
|
"%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"
|
|
)
|
|
|
|
logging.basicConfig(format=formatter, level=logging.INFO)
|
|
|
|
compute_fbank_yesno()
|