noise_reduction package#

Submodules#

noise_reduction.noise_reduction module#

class noise_reduction.noise_reduction.DFN(target_directory: pathlib.Path, verbose: bool = True, silence_threshold: Optional[float] = None, pad: bool = True, atten_lim_db: Optional[int] = None, **kwargs)[source]#

Bases: noise_reduction.noise_reduction.ReduceNoiseBase

clean_audio(data: torch.Tensor) → torch.Tensor[source]#

Clean the audio from noise. Here you should implement the noise reduction algorithm.

Parameters

data – The audio data to clean.

Returns

The cleaned audio.

load_audio(file: str) → torch.Tensor[source]#

Load the audio from a file.

Parameters

file – The file to load the audio from.

Returns

A tuple of: - the audio data - the sample rate

save_audio(audio: numpy.ndarray, target_path: pathlib.Path)[source]#

Save the audio to a file.

Parameters

  • audio – The audio to save.

  • target_path – The target path to save the audio to.

class noise_reduction.noise_reduction.ReduceNoise(target_directory: pathlib.Path, verbose: bool = True, silence_threshold: Optional[float] = None, sample_rate: int = 16000, duration: Optional[int] = None, channel: Optional[int] = None)[source]#

Bases: noise_reduction.noise_reduction.ReduceNoiseBase

clean_audio(data: numpy.ndarray) → numpy.ndarray[source]#

Clean the audio from noise. Here you should implement the noise reduction algorithm.

Parameters

data – The audio data to clean.

Returns

The cleaned audio.

load_audio(file: str) → numpy.ndarray[source]#

Load the audio from a file.

Parameters

file – The file to load the audio from.

Returns

A tuple of: - the audio data - the sample rate

save_audio(audio: numpy.ndarray, target_path: pathlib.Path)[source]#

Save the audio to a file.

Parameters

  • audio – The audio to save.

  • target_path – The target path to save the audio to.

class noise_reduction.noise_reduction.ReduceNoiseBase(target_directory: pathlib.Path, verbose: bool = True, silence_threshold: Optional[float] = None)[source]#

Bases: object

Base class for noise reduction. This class is aimed to be inherited by specific noise reduction algorithms. You must implement the following methods: - clean_audio: The method to clean the audio, where the noise reduction algorithm is implemented. - save_audio: The method to save the audio to a file. - load_audio: The method to load the audio from a file.

After implementing the above methods, you can use the reduce_noise method to reduce noise from audio files.

abstract clean_audio(data) → Union[numpy.ndarray, torch.Tensor][source]#

Clean the audio from noise. Here you should implement the noise reduction algorithm.

Parameters

data – The audio data to clean.

Returns

The cleaned audio.

abstract load_audio(file: str) → Tuple[Union[numpy.ndarray, torch.Tensor], int][source]#

Load the audio from a file.

Parameters

file – The file to load the audio from.

Returns

A tuple of: - the audio data - the sample rate

reduce_noise(audio_file: pathlib.Path) → Tuple[bool, Tuple[str, str]][source]#

Reduce noise from the given audio file.

Parameters

audio_file – The audio file to reduce noise from.

Returns

A tuple of: - a boolean indicating whether an error occurred - a tuple of:

  • audio file name

  • target path in case of success / error message in case of failure.

remove_silence(audio: numpy.ndarray)[source]#

Remove silence sections from the audio.

Parameters

audio – The audio to remove silence from.

Returns

The audio without silence.

abstract save_audio(audio: numpy.ndarray, target_path: pathlib.Path)[source]#

Save the audio to a file.

Parameters

  • audio – The audio to save.

  • target_path – The target path to save the audio to.

update_to_wav_suffix(audio_file: pathlib.Path)[source]#
noise_reduction.noise_reduction.reduce_noise(audio_source: str, target_directory: str, sample_rate: int = 16000, duration: Optional[int] = None, channel: Optional[int] = None, silence_threshold: Optional[float] = None, use_multiprocessing: int = 0, verbose: bool = True)[source]#

Reduce noise from audio file or directory containing audio files. The audio files must be in .wav format. The cleaned audio files will be saved in the target_directory. For information about the noise reduction algorithm see: https://github.com/timsainb/noisereduce Notice that the saved files are in wav format, even if the original files are in other format.

Parameters

  • audio_source – path to audio file or directory containing audio files

  • target_directory – path to directory to save the cleaned audio files.

  • sample_rate – Number of samples in one second in the audio file. Pass None to keep the original sample rate.

  • duration – Duration of the audio file to clean in seconds. Pass None to keep the original duration.

  • channel – Channel to clean. Pass the number of the channel to clean. To clean all channels pass None.

  • silence_threshold – The threshold to remove silence from the audio, in dB. If None, no silence removal is performed.

  • use_multiprocessing – Number of processes to use for cleaning the audio files. If 0, no multiprocessing is used.

  • verbose – Verbosity level. If True, display progress bar.

noise_reduction.noise_reduction.reduce_noise_dfn(audio_source: str, target_directory: str, pad: bool = True, atten_lim_db: Optional[int] = None, silence_threshold: Optional[float] = None, use_multiprocessing: int = 0, verbose: bool = True, **kwargs)[source]#

Reduce noise from audio files using DeepFilterNet. For more information about the noise reduction algorithm see: https://github.com/Rikorose/DeepFilterNet Notice that the saved files are in wav format, even if the original files are in other format.

Parameters

  • audio_source – path to audio file or directory of audio files

  • target_directory – path to target directory to save cleaned audio files

  • pad – whether to pad the audio file with zeros before cleaning

  • atten_lim_db – maximum attenuation in dB

  • silence_threshold – the threshold to remove silence from the audio, in dB. If None, no silence removal is performed.

  • use_multiprocessing – Number of processes to use for cleaning the audio files. If 0, no multiprocessing is used.

  • verbose – verbosity level. If True, display progress bar and logs.

  • kwargs – additional arguments to pass to torchaudio.load(). For more information see: https://pytorch.org/audio/stable/generated/torchaudio.load.html

Module contents#