Unable to normalize segment
Created by: shoegazerstella
This error appears quite often during my training. Any idea on how to solve it? maybe doing some preprocessing on the audio?
[WARNING 2019-12-18 17:38:59,189 reader.py:487] Your reader has raised an exception!
Exception in thread Thread-120:
Traceback (most recent call last):
File "/home/stella/.conda/envs/paddle/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/home/stella/.conda/envs/paddle/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
File "/home/stella/.conda/envs/paddle/lib/python2.7/site-packages/paddle/fluid/reader.py", line 488, in __thread_main__
six.reraise(*sys.exc_info())
File "/home/stella/.conda/envs/paddle/lib/python2.7/site-packages/paddle/fluid/reader.py", line 468, in __thread_main__
for tensors in self._tensor_reader():
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/data.py", line 200, in batch_reader
for instance in instance_reader():
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/data.py", line 279, in reader
instance["text"]),
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/data.py", line 121, in process_utterance
speech_segment, self._keep_transcription_text)
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/featurizer/speech_featurizer.py", line 76, in featurize
audio_feature = self._audio_featurizer.featurize(speech_segment)
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/featurizer/audio_featurizer.py", line 86, in featurize
audio_segment.normalize(target_db=self._target_dB)
File "/mnt/Data/stella/paddle/DeepSpeech/data_utils/audio.py", line 345, in normalize
(target_db, max_gain_db))
ValueError: Unable to normalize segment to -20.000000 dB because the the probable gain have exceeds max_gain_db (300.000000 dB)
Thanks!