fix format

examples/dataset/ted_en_zh/ted_en_zh.py

@@ -73,7 +73,6 @@ def create_manifest(data_dir, manifest_path_prefix):
                 audio_data, samplerate = soundfile.read(audio_path)
                 duration = float(len(audio_data) / samplerate)
 
-
                 translation_str = " ".join(translation.split())
                 trancription_str = " ".join(trancription.split())
                 json_lines.append(

examples/dataset/thchs30/thchs30.py

@@ -124,7 +124,7 @@ def create_manifest(data_dir, manifest_path_prefix):
                     json.dumps(
                         {
                             'utt': audio_id,
-                            'utt2spk', spk,
+                            'utt2spk': spk,
                             'feat': audio_path,
                             'feat_shape': (duration, ),  # second
                             'text': word_text,  # charactor

examples/dataset/timit/timit_kaldi_standard_split.py

@@ -22,9 +22,9 @@ import argparse
 import codecs
 import json
 import os
+from pathlib import Path
 
 import soundfile
-from pathlib import Path
 
 parser = argparse.ArgumentParser(description=__doc__)
 parser.add_argument(

examples/wenetspeech/asr1/local/extract_meta.py

@@ -1,6 +1,18 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# 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.
 # Copyright 2021  Xiaomi Corporation (Author: Yongqing Wang)
 #                 Mobvoi Inc(Author: Di Wu, Binbin Zhang)
-
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -12,11 +24,10 @@
 # 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.
-
-import sys
-import os
 import argparse
 import json
+import os
+import sys
 
 
 def get_args():
@@ -85,13 +96,13 @@ def meta_analysis(input_json, output_dir):
                             else:
                                 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')
                                 segment_sub_names = " ".join(segment_subsets)
                                 utt2subsets.write(
                                     f'{sid}\t{segment_sub_names}\n')
 
+
 def main():
     args = get_args()
 

examples/wenetspeech/asr1/local/process_opus.py

@@ -1,5 +1,17 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# 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.
 # Copyright 2021  NPU, ASLP Group (Author: Qijie Shao)
-
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
@@ -11,14 +23,12 @@
 # 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.
-
 # process_opus.py: segmentation and downsampling of opus audio
-
 # usage: python3 process_opus.py wav.scp segments output_wav.scp
+import os
+import sys
 
 from pydub import AudioSegment
-import sys
-import os
 
 
 def read_file(wav_scp, segments):

paddlespeech/s2t/exps/u2/model.py

@@ -24,15 +24,10 @@ import jsonlines
 import numpy as np
 import paddle
 from paddle import distributed as dist
-from paddle.io import DataLoader
 from yacs.config import CfgNode
 
 from paddlespeech.s2t.frontend.featurizer import TextFeaturizer
-from paddlespeech.s2t.io.collator import SpeechCollator
 from paddlespeech.s2t.io.dataloader import BatchDataLoader
-from paddlespeech.s2t.io.dataset import ManifestDataset
-from paddlespeech.s2t.io.sampler import SortagradBatchSampler
-from paddlespeech.s2t.io.sampler import SortagradDistributedBatchSampler
 from paddlespeech.s2t.models.u2 import U2Model
 from paddlespeech.s2t.training.optimizer import OptimizerFactory
 from paddlespeech.s2t.training.reporter import ObsScope
@@ -215,7 +210,7 @@ class U2Trainer(Trainer):
                             msg += f"{v:>.8f}" if isinstance(v,
                                                              float) else f"{v}"
                             msg += f" {k.split(',')[1]}" if len(
-                                k.split(',')) == 2 else f""
+                                k.split(',')) == 2 else ""
                             msg += ","
                         msg = msg[:-1]  # remove the last ","
                         if (batch_index + 1

paddlespeech/s2t/frontend/featurizer/text_featurizer.py

@@ -57,7 +57,7 @@ class TextFeaturizer():
                 vocab_filepath, maskctc)
             self.vocab_size = len(self.vocab_list)
         else:
-            logger.warning(f"TextFeaturizer: not have vocab file.")
+            logger.warning("TextFeaturizer: not have vocab file.")
 
         if unit_type == 'spm':
             spm_model = spm_model_prefix + '.model'