mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
5a0b9bcb23
* Fix an error in TDNN-LSTM training. * WIP: Refactoring * Refactor transformer.py * Remove unused code. * Minor fixes.
83 lines
2.1 KiB
Python
Executable File
83 lines
2.1 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
# Copyright (c) 2021 Xiaomi Corporation (authors: Fangjun Kuang)
|
|
"""
|
|
This file downloads the following LibriSpeech LM files:
|
|
|
|
- 3-gram.pruned.1e-7.arpa.gz
|
|
- 4-gram.arpa.gz
|
|
- librispeech-vocab.txt
|
|
- librispeech-lexicon.txt
|
|
|
|
from http://www.openslr.org/resources/11
|
|
and save them in the user provided directory.
|
|
|
|
Files are not re-downloaded if they already exist.
|
|
|
|
Usage:
|
|
./local/download_lm.py --out-dir ./download/lm
|
|
"""
|
|
|
|
import argparse
|
|
import gzip
|
|
import logging
|
|
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
from lhotse.utils import urlretrieve_progress
|
|
from tqdm.auto import tqdm
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--out-dir", type=str, help="Output directory.")
|
|
|
|
args = parser.parse_args()
|
|
return args
|
|
|
|
|
|
def main(out_dir: str):
|
|
url = "http://www.openslr.org/resources/11"
|
|
out_dir = Path(out_dir)
|
|
|
|
files_to_download = (
|
|
"3-gram.pruned.1e-7.arpa.gz",
|
|
"4-gram.arpa.gz",
|
|
"librispeech-vocab.txt",
|
|
"librispeech-lexicon.txt",
|
|
)
|
|
|
|
for f in tqdm(files_to_download, desc="Downloading LibriSpeech LM files"):
|
|
filename = out_dir / f
|
|
if filename.is_file() is False:
|
|
urlretrieve_progress(
|
|
f"{url}/{f}",
|
|
filename=filename,
|
|
desc=f"Downloading {filename}",
|
|
)
|
|
else:
|
|
logging.info(f"{filename} already exists - skipping")
|
|
|
|
if ".gz" in str(filename):
|
|
unzipped = Path(os.path.splitext(filename)[0])
|
|
if unzipped.is_file() is False:
|
|
with gzip.open(filename, "rb") as f_in:
|
|
with open(unzipped, "wb") as f_out:
|
|
shutil.copyfileobj(f_in, f_out)
|
|
else:
|
|
logging.info(f"{unzipped} already exist - skipping")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
formatter = (
|
|
"%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"
|
|
)
|
|
|
|
logging.basicConfig(format=formatter, level=logging.INFO)
|
|
|
|
args = get_args()
|
|
logging.info(f"out_dir: {args.out_dir}")
|
|
|
|
main(out_dir=args.out_dir)
|