mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-09 18:12:19 +00:00
98 lines
3.0 KiB
Python
Executable File
98 lines
3.0 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
"""
|
|
This file computes fbank features of the musan dataset.
|
|
Its looks for manifests in the directory data/manifests
|
|
and generated fbank features are saved in data/fbank.
|
|
"""
|
|
|
|
import os
|
|
import subprocess
|
|
from contextlib import contextmanager
|
|
from pathlib import Path
|
|
|
|
from lhotse import CutSet, Fbank, FbankConfig, LilcomHdf5Writer, combine
|
|
from lhotse.recipes.utils import read_manifests_if_cached
|
|
|
|
|
|
@contextmanager
|
|
def get_executor():
|
|
# We'll either return a process pool or a distributed worker pool.
|
|
# Note that this has to be a context manager because we might use multiple
|
|
# context manager ("with" clauses) inside, and this way everything will
|
|
# free up the resources at the right time.
|
|
try:
|
|
# If this is executed on the CLSP grid, we will try to use the
|
|
# Grid Engine to distribute the tasks.
|
|
# Other clusters can also benefit from that, provided a cluster-specific wrapper.
|
|
# (see https://github.com/pzelasko/plz for reference)
|
|
#
|
|
# The following must be installed:
|
|
# $ pip install dask distributed
|
|
# $ pip install git+https://github.com/pzelasko/plz
|
|
name = subprocess.check_output("hostname -f", shell=True, text=True)
|
|
if name.strip().endswith(".clsp.jhu.edu"):
|
|
import plz
|
|
from distributed import Client
|
|
|
|
with plz.setup_cluster() as cluster:
|
|
cluster.scale(80)
|
|
yield Client(cluster)
|
|
return
|
|
except:
|
|
pass
|
|
# No need to return anything - compute_and_store_features
|
|
# will just instantiate the pool itself.
|
|
yield None
|
|
|
|
|
|
def compute_fbank_musan():
|
|
src_dir = Path("data/manifests")
|
|
output_dir = Path("data/fbank")
|
|
num_jobs = min(15, os.cpu_count())
|
|
num_mel_bins = 80
|
|
|
|
dataset_parts = (
|
|
"music",
|
|
"speech",
|
|
"noise",
|
|
)
|
|
manifests = read_manifests_if_cached(
|
|
dataset_parts=dataset_parts, output_dir=src_dir
|
|
)
|
|
assert manifests is not None
|
|
|
|
musan_cuts_path = output_dir / "cuts_musan.json.gz"
|
|
|
|
if musan_cuts_path.is_file():
|
|
print(f"{musan_cuts_path} already exists - skipping")
|
|
return
|
|
|
|
print("Extracting features for Musan")
|
|
|
|
extractor = Fbank(FbankConfig(num_mel_bins=num_mel_bins))
|
|
|
|
with get_executor() as ex: # Initialize the executor only once.
|
|
# create chunks of Musan with duration 5 - 10 seconds
|
|
musan_cuts = (
|
|
CutSet.from_manifests(
|
|
recordings=combine(
|
|
part["recordings"] for part in manifests.values()
|
|
)
|
|
)
|
|
.cut_into_windows(10.0)
|
|
.filter(lambda c: c.duration > 5)
|
|
.compute_and_store_features(
|
|
extractor=extractor,
|
|
storage_path=f"{output_dir}/feats_musan",
|
|
num_jobs=num_jobs if ex is None else 80,
|
|
executor=ex,
|
|
storage_type=LilcomHdf5Writer,
|
|
)
|
|
)
|
|
musan_cuts.to_json(musan_cuts_path)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
compute_fbank_musan()
|