format code,test=doc

.pre-commit-config.yaml

@@ -50,12 +50,13 @@ repos:
         entry: bash .pre-commit-hooks/clang-format.hook -i
         language: system
         files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|cuh|proto)$
+        exclude: (?=speechx/speechx/kaldi).*(\.cpp|\.cc|\.h|\.py)$
     -   id: copyright_checker
         name: copyright_checker
         entry: python .pre-commit-hooks/copyright-check.hook
         language: system
         files: \.(c|cc|cxx|cpp|cu|h|hpp|hxx|proto|py)$
-        exclude: (?=third_party|pypinyin).*(\.cpp|\.h|\.py)$
+        exclude: (?=third_party|pypinyin|speechx/speechx/kaldi).*(\.cpp|\.cc|\.h|\.py)$
 -   repo: https://github.com/asottile/reorder_python_imports
     rev: v2.4.0
     hooks:

dataset/voxceleb/voxceleb1.py

@@ -80,6 +80,7 @@ parser.add_argument(
 
 args = parser.parse_args()
 
+
 def create_manifest(data_dir, manifest_path_prefix):
     print("Creating manifest %s ..." % manifest_path_prefix)
     json_lines = []
@@ -128,6 +129,7 @@ def create_manifest(data_dir, manifest_path_prefix):
         print(f"{total_text / total_sec} text/sec", file=f)
         print(f"{total_sec / total_num} sec/utt", file=f)
 
+
 def prepare_dataset(base_url, data_list, target_dir, manifest_path,
                     target_data):
     if not os.path.exists(target_dir):
@@ -164,6 +166,7 @@ def prepare_dataset(base_url, data_list, target_dir, manifest_path,
     # create the manifest file
     create_manifest(data_dir=target_dir, manifest_path_prefix=manifest_path)
 
+
 def main():
     if args.target_dir.startswith('~'):
         args.target_dir = os.path.expanduser(args.target_dir)
@@ -184,5 +187,6 @@ def main():
 
     print("Manifest prepare done!")
 
+
 if __name__ == '__main__':
     main()

examples/ami/sd0/local/ami_prepare.py

@@ -22,19 +22,17 @@ Authors
  * qingenz123@126.com (Qingen ZHAO) 2022
 
 """
-
-import os
-import logging
 import argparse
-import xml.etree.ElementTree as et
 import glob
 import json
-from ami_splits import get_AMI_split
+import logging
+import os
+import xml.etree.ElementTree as et
 from distutils.util import strtobool
 
-from dataio import (
+from ami_splits import get_AMI_split
-    load_pkl,
+from dataio import load_pkl
-    save_pkl, )
+from dataio import save_pkl
 
 logger = logging.getLogger(__name__)
 SAMPLERATE = 16000

examples/voxceleb/sv0/local/make_voxceleb_kaldi_trial.py

@@ -12,28 +12,30 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 """
 Make VoxCeleb1 trial of kaldi format
 this script creat the test trial from kaldi trial voxceleb1_test_v2.txt or official trial veri_test2.txt 
 to kaldi trial format
 """
-
 import argparse
 import codecs
 import os
 
 parser = argparse.ArgumentParser(description=__doc__)
-parser.add_argument("--voxceleb_trial",
+parser.add_argument(
-                    default="voxceleb1_test_v2",
+    "--voxceleb_trial",
-                    type=str,
+    default="voxceleb1_test_v2",
-                    help="VoxCeleb trial file. Default we use the kaldi trial voxceleb1_test_v2.txt")
+    type=str,
-parser.add_argument("--trial",
+    help="VoxCeleb trial file. Default we use the kaldi trial voxceleb1_test_v2.txt"
-                    default="data/test/trial",
+)
-                    type=str,
+parser.add_argument(
-                    help="Kaldi format trial file")
+    "--trial",
+    default="data/test/trial",
+    type=str,
+    help="Kaldi format trial file")
 args = parser.parse_args()
 
+
 def main(voxceleb_trial, trial):
     """
         VoxCeleb provide several trial file, which format is different with kaldi format.
@@ -58,7 +60,9 @@ def main(voxceleb_trial, trial):
     """
     print("Start convert the voxceleb trial to kaldi format")
     if not os.path.exists(voxceleb_trial):
-        raise RuntimeError("{} does not exist. Pleas input the correct file path".format(voxceleb_trial))
+        raise RuntimeError(
+            "{} does not exist. Pleas input the correct file path".format(
+                voxceleb_trial))
 
     trial_dirname = os.path.dirname(trial)
     if not os.path.exists(trial_dirname):
@@ -66,9 +70,9 @@ def main(voxceleb_trial, trial):
 
     with codecs.open(voxceleb_trial, 'r', encoding='utf-8') as f, \
          codecs.open(trial, 'w', encoding='utf-8') as w:
-         for line in f:
+        for line in f:
             target_or_nontarget, path1, path2 = line.strip().split()
-             
+
             utt_id1 = "-".join(path1.split("/"))
             utt_id2 = "-".join(path2.split("/"))
             target = "nontarget"
@@ -77,5 +81,6 @@ def main(voxceleb_trial, trial):
             w.write("{} {} {}\n".format(utt_id1, utt_id2, target))
     print("Convert the voxceleb trial to kaldi format successfully")
 
+
 if __name__ == "__main__":
     main(args.voxceleb_trial, args.trial)

paddlespeech/__init__.py

@@ -11,14 +11,3 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
-
-
-
-
-
-
-
-
-
-

paddlespeech/cli/asr/infer.py

@@ -413,7 +413,8 @@ class ASRExecutor(BaseExecutor):
     def _check(self, audio_file: str, sample_rate: int, force_yes: bool):
         self.sample_rate = sample_rate
         if self.sample_rate != 16000 and self.sample_rate != 8000:
-            logger.error("invalid sample rate, please input --sr 8000 or --sr 16000")
+            logger.error(
+                "invalid sample rate, please input --sr 8000 or --sr 16000")
             return False
 
         if isinstance(audio_file, (str, os.PathLike)):

paddlespeech/s2t/io/utility.py

@@ -11,8 +11,8 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from typing import List
 from io import BytesIO
+from typing import List
 
 import numpy as np
 

paddlespeech/t2s/datasets/dataset.py

@@ -258,4 +258,4 @@ class ChainDataset(Dataset):
                 return dataset[i]
             i -= len(dataset)
 
-        raise IndexError("dataset index out of range")
+        raise IndexError("dataset index out of range")

utils/DER.py

@@ -23,10 +23,11 @@ Credits
  This code is adapted from https://github.com/nryant/dscore
 """
 import argparse
-from distutils.util import strtobool
 import os
 import re
 import subprocess
+from distutils.util import strtobool
+
 import numpy as np
 
 FILE_IDS = re.compile(r"(?<=Speaker Diarization for).+(?=\*\*\*)")