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