From ca79f9c404e68fcb55a09200abbe8547474605fe Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期四, 25 五月 2023 17:02:24 +0800
Subject: [PATCH] update repo
---
egs/wenetspeech/conformer/local/extract_meta.py | 90 +++++++++++++++++++++++++-------------------
1 files changed, 51 insertions(+), 39 deletions(-)
diff --git a/egs/wenetspeech/conformer/local/extract_meta.py b/egs/wenetspeech/conformer/local/extract_meta.py
index ce2871d..6074162 100755
--- a/egs/wenetspeech/conformer/local/extract_meta.py
+++ b/egs/wenetspeech/conformer/local/extract_meta.py
@@ -13,20 +13,22 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-import sys
-import os
import argparse
import json
+import os
+import sys
def get_args():
- parser = argparse.ArgumentParser(description="""
+ parser = argparse.ArgumentParser(
+ description="""
This script is used to process raw json dataset of WenetSpeech,
where the long wav is splitinto segments and
data of wenet format is generated.
- """)
- parser.add_argument('input_json', help="""Input json file of WenetSpeech""")
- parser.add_argument('output_dir', help="""Output dir for prepared data""")
+ """
+ )
+ parser.add_argument("input_json", help="""Input json file of WenetSpeech""")
+ parser.add_argument("output_dir", help="""Output dir for prepared data""")
args = parser.parse_args()
return args
@@ -39,58 +41,68 @@
os.makedirs(output_dir)
try:
- with open(input_json, 'r') as injson:
+ with open(input_json, "r") as injson:
json_data = json.load(injson)
except Exception:
- sys.exit(f'Failed to load input json file: {input_json}')
+ sys.exit(f"Failed to load input json file: {input_json}")
else:
- if json_data['audios'] is not None:
- with open(f'{output_dir}/text', 'w') as utt2text, \
- open(f'{output_dir}/segments', 'w') as segments, \
- open(f'{output_dir}/utt2dur', 'w') as utt2dur, \
- open(f'{output_dir}/wav.scp', 'w') as wavscp, \
- open(f'{output_dir}/utt2subsets', 'w') as utt2subsets, \
- open(f'{output_dir}/reco2dur', 'w') as reco2dur:
- for long_audio in json_data['audios']:
+ if json_data["audios"] is not None:
+ with open(f"{output_dir}/text", "w") as utt2text, open(
+ f"{output_dir}/segments", "w"
+ ) as segments, open(f"{output_dir}/utt2dur", "w") as utt2dur, open(
+ f"{output_dir}/wav.scp", "w"
+ ) as wavscp, open(
+ f"{output_dir}/utt2subsets", "w"
+ ) as utt2subsets, open(
+ f"{output_dir}/reco2dur", "w"
+ ) as reco2dur:
+ for long_audio in json_data["audios"]:
try:
long_audio_path = os.path.realpath(
- os.path.join(input_dir, long_audio['path']))
- aid = long_audio['aid']
- segments_lists = long_audio['segments']
- duration = long_audio['duration']
- assert (os.path.exists(long_audio_path))
+ os.path.join(input_dir, long_audio["path"])
+ )
+ aid = long_audio["aid"]
+ segments_lists = long_audio["segments"]
+ duration = long_audio["duration"]
+ assert os.path.exists(long_audio_path)
except AssertionError:
- print(f'''Warning: {aid} something is wrong,
- maybe AssertionError, skipped''')
+ print(
+ f"""Warning: {aid} something is wrong,
+ maybe AssertionError, skipped"""
+ )
continue
except Exception:
- print(f'''Warning: {aid} something is wrong, maybe the
- error path: {long_audio_path}, skipped''')
+ print(
+ f"""Warning: {aid} something is wrong, maybe the
+ error path: {long_audio_path}, skipped"""
+ )
continue
else:
- wavscp.write(f'{aid}\t{long_audio_path}\n')
- reco2dur.write(f'{aid}\t{duration}\n')
+ wavscp.write(f"{aid}\t{long_audio_path}\n")
+ reco2dur.write(f"{aid}\t{duration}\n")
for segment_file in segments_lists:
try:
- sid = segment_file['sid']
- start_time = segment_file['begin_time']
- end_time = segment_file['end_time']
+ sid = segment_file["sid"]
+ start_time = segment_file["begin_time"]
+ end_time = segment_file["end_time"]
dur = end_time - start_time
- text = segment_file['text']
+ text = segment_file["text"]
segment_subsets = segment_file["subsets"]
except Exception:
- print(f'''Warning: {segment_file} something
- is wrong, skipped''')
+ print(
+ f"""Warning: {segment_file} something
+ is wrong, skipped"""
+ )
continue
else:
- utt2text.write(f'{sid}\t{text}\n')
+ utt2text.write(f"{sid}\t{text}\n")
segments.write(
- f'{sid}\t{aid}\t{start_time}\t{end_time}\n'
+ f"{sid}\t{aid}\t{start_time}\t{end_time}\n"
)
- utt2dur.write(f'{sid}\t{dur}\n')
+ utt2dur.write(f"{sid}\t{dur}\n")
segment_sub_names = " ".join(segment_subsets)
- utt2subsets.write(
- f'{sid}\t{segment_sub_names}\n')
+ utt2subsets.write(f"{sid}\t{segment_sub_names}\n")
+
def main():
args = get_args()
@@ -98,5 +110,5 @@
meta_analysis(args.input_json, args.output_dir)
-if __name__ == '__main__':
+if __name__ == "__main__":
main()
--
Gitblit v1.9.1