From 2eb69485a9d4ba64256688f5545389d70b75082c Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 11 五月 2023 16:36:20 +0800
Subject: [PATCH] update repo
---
egs/librispeech/conformer/local/data_prep.sh | 0
egs/librispeech/conformer/local/spm_train.py | 12 +++
egs/librispeech/conformer/local/download_and_untar.sh | 97 ++++++++++++++++++++++++
egs/librispeech/conformer/local/spm_encode.py | 98 ++++++++++++++++++++++++
4 files changed, 207 insertions(+), 0 deletions(-)
diff --git a/egs/librispeech/conformer/local/data_prep_librispeech.sh b/egs/librispeech/conformer/local/data_prep.sh
similarity index 100%
rename from egs/librispeech/conformer/local/data_prep_librispeech.sh
rename to egs/librispeech/conformer/local/data_prep.sh
diff --git a/egs/librispeech/conformer/local/download_and_untar.sh b/egs/librispeech/conformer/local/download_and_untar.sh
new file mode 100755
index 0000000..fe322e4
--- /dev/null
+++ b/egs/librispeech/conformer/local/download_and_untar.sh
@@ -0,0 +1,97 @@
+#!/usr/bin/env bash
+
+# Copyright 2014 Johns Hopkins University (author: Daniel Povey)
+# Apache 2.0
+
+remove_archive=false
+
+if [ "$1" == --remove-archive ]; then
+ remove_archive=true
+ shift
+fi
+
+if [ $# -ne 3 ]; then
+ echo "Usage: $0 [--remove-archive] <data-base> <url-base> <corpus-part>"
+ echo "e.g.: $0 /export/a15/vpanayotov/data www.openslr.org/resources/11 dev-clean"
+ echo "With --remove-archive it will remove the archive after successfully un-tarring it."
+ echo "<corpus-part> can be one of: dev-clean, test-clean, dev-other, test-other,"
+ echo " train-clean-100, train-clean-360, train-other-500."
+ exit 1
+fi
+
+data=$1
+url=$2
+part=$3
+
+if [ ! -d "$data" ]; then
+ echo "$0: no such directory $data"
+ exit 1
+fi
+
+part_ok=false
+list="dev-clean test-clean dev-other test-other train-clean-100 train-clean-360 train-other-500"
+for x in $list; do
+ if [ "$part" == $x ]; then part_ok=true; fi
+done
+if ! $part_ok; then
+ echo "$0: expected <corpus-part> to be one of $list, but got '$part'"
+ exit 1
+fi
+
+if [ -z "$url" ]; then
+ echo "$0: empty URL base."
+ exit 1
+fi
+
+if [ -f $data/LibriSpeech/$part/.complete ]; then
+ echo "$0: data part $part was already successfully extracted, nothing to do."
+ exit 0
+fi
+
+
+# sizes of the archive files in bytes. This is some older versions.
+sizes_old="371012589 347390293 379743611 361838298 6420417880 23082659865 30626749128"
+# sizes_new is the archive file sizes of the final release. Some of these sizes are of
+# things we probably won't download.
+sizes_new="337926286 314305928 695964615 297279345 87960560420 33373768 346663984 328757843 6387309499 23049477885 30593501606"
+
+if [ -f $data/$part.tar.gz ]; then
+ size=$(/bin/ls -l $data/$part.tar.gz | awk '{print $5}')
+ size_ok=false
+ for s in $sizes_old $sizes_new; do if [ $s == $size ]; then size_ok=true; fi; done
+ if ! $size_ok; then
+ echo "$0: removing existing file $data/$part.tar.gz because its size in bytes $size"
+ echo "does not equal the size of one of the archives."
+ rm $data/$part.tar.gz
+ else
+ echo "$data/$part.tar.gz exists and appears to be complete."
+ fi
+fi
+
+if [ ! -f $data/$part.tar.gz ]; then
+ if ! which wget >/dev/null; then
+ echo "$0: wget is not installed."
+ exit 1
+ fi
+ full_url=$url/$part.tar.gz
+ echo "$0: downloading data from $full_url. This may take some time, please be patient."
+
+ if ! wget -P $data --no-check-certificate $full_url; then
+ echo "$0: error executing wget $full_url"
+ exit 1
+ fi
+fi
+
+if ! tar -C $data -xvzf $data/$part.tar.gz; then
+ echo "$0: error un-tarring archive $data/$part.tar.gz"
+ exit 1
+fi
+
+touch $data/LibriSpeech/$part/.complete
+
+echo "$0: Successfully downloaded and un-tarred $data/$part.tar.gz"
+
+if $remove_archive; then
+ echo "$0: removing $data/$part.tar.gz file since --remove-archive option was supplied."
+ rm $data/$part.tar.gz
+fi
diff --git a/egs/librispeech/conformer/local/spm_encode.py b/egs/librispeech/conformer/local/spm_encode.py
new file mode 100755
index 0000000..9e1c15f
--- /dev/null
+++ b/egs/librispeech/conformer/local/spm_encode.py
@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+# Copyright (c) Facebook, Inc. and its affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in
+# https://github.com/pytorch/fairseq/blob/master/LICENSE
+
+
+import argparse
+import contextlib
+import sys
+
+import sentencepiece as spm
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument("--model", required=True,
+ help="sentencepiece model to use for encoding")
+ parser.add_argument("--inputs", nargs="+", default=['-'],
+ help="input files to filter/encode")
+ parser.add_argument("--outputs", nargs="+", default=['-'],
+ help="path to save encoded outputs")
+ parser.add_argument("--output_format", choices=["piece", "id"], default="piece")
+ parser.add_argument("--min-len", type=int, metavar="N",
+ help="filter sentence pairs with fewer than N tokens")
+ parser.add_argument("--max-len", type=int, metavar="N",
+ help="filter sentence pairs with more than N tokens")
+ args = parser.parse_args()
+
+ assert len(args.inputs) == len(args.outputs), \
+ "number of input and output paths should match"
+
+ sp = spm.SentencePieceProcessor()
+ sp.Load(args.model)
+
+ if args.output_format == "piece":
+ def encode(l):
+ return sp.EncodeAsPieces(l)
+ elif args.output_format == "id":
+ def encode(l):
+ return list(map(str, sp.EncodeAsIds(l)))
+ else:
+ raise NotImplementedError
+
+ if args.min_len is not None or args.max_len is not None:
+ def valid(line):
+ return (
+ (args.min_len is None or len(line) >= args.min_len) and
+ (args.max_len is None or len(line) <= args.max_len)
+ )
+ else:
+ def valid(lines):
+ return True
+
+ with contextlib.ExitStack() as stack:
+ inputs = [
+ stack.enter_context(open(input, "r", encoding="utf-8"))
+ if input != "-" else sys.stdin
+ for input in args.inputs
+ ]
+ outputs = [
+ stack.enter_context(open(output, "w", encoding="utf-8"))
+ if output != "-" else sys.stdout
+ for output in args.outputs
+ ]
+
+ stats = {
+ "num_empty": 0,
+ "num_filtered": 0,
+ }
+
+ def encode_line(line):
+ line = line.strip()
+ if len(line) > 0:
+ line = encode(line)
+ if valid(line):
+ return line
+ else:
+ stats["num_filtered"] += 1
+ else:
+ stats["num_empty"] += 1
+ return None
+
+ for i, lines in enumerate(zip(*inputs), start=1):
+ enc_lines = list(map(encode_line, lines))
+ if not any(enc_line is None for enc_line in enc_lines):
+ for enc_line, output_h in zip(enc_lines, outputs):
+ print(" ".join(enc_line), file=output_h)
+ if i % 10000 == 0:
+ print("processed {} lines".format(i), file=sys.stderr)
+
+ print("skipped {} empty lines".format(stats["num_empty"]), file=sys.stderr)
+ print("filtered {} lines".format(stats["num_filtered"]), file=sys.stderr)
+
+
+if __name__ == "__main__":
+ main()
diff --git a/egs/librispeech/conformer/local/spm_train.py b/egs/librispeech/conformer/local/spm_train.py
new file mode 100755
index 0000000..134a0b1
--- /dev/null
+++ b/egs/librispeech/conformer/local/spm_train.py
@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+# Copyright (c) Facebook, Inc. and its affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in the
+# https://github.com/pytorch/fairseq/blob/master/LICENSE
+import sys
+
+import sentencepiece as spm
+
+if __name__ == "__main__":
+ spm.SentencePieceTrainer.Train(" ".join(sys.argv[1:]))
--
Gitblit v1.9.1