o 7wi @s4dZddlZddlZddlZGdddejjZdS)a Codec Augmentation via torchaudio This library provides codec augmentation techniques in torchaudio for enhanced audio data processing. For detailed guidance and usage examples, refer to the tutorial at: https://pytorch.org/audio/stable/tutorials/audio_data_augmentation_tutorial.html Note: This code is compatible with FFmpeg as the torchaudio backend. When using FFmpeg2, the maximum number of samples for processing is limited to 16. Authors * Mirco Ravanelli 2023 Ncs4eZdZdZd fdd Zd ddZdd ZZS) CodecAugmenta Apply random audio codecs to input waveforms using torchaudio. This class provides an interface for applying codec augmentation techniques to audio data. Arguments --------- sample_rate: int The sample rate of the input waveform. Example ------- >>> waveform = torch.rand(4, 16000) >>> if torchaudio.list_audio_backends()[0] == 'ffmpeg': ... augmenter = CodecAugment(16000) ... output_waveform = augmenter(waveform) >cst||_gd|_dS)N))wav pcm_mulaw)mp3N)g722N)super__init__ sample_rateavailable_format_encoders)selfr  __class__V/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/speechbrain/augment/codec.pyr *s zCodecAugment.__init__NcCs@tjj||d}||ddd|j}|dd|jS)a Apply the selected audio codec. Arguments ---------- waveform: torch.Tensor Input waveform of shape `[batch, time]`. format: str The audio format to use (e.g., "wav", "mp3"). Default is None. encoder: str The encoder to use for the format (e.g., "opus", "vorbis"). Default is None. Returns --------- torch.Tensor: Coded version of the input waveform of shape `[batch, time]`. formatencoderrcpu) torchaudioio AudioEffectorapply transposetor device)r waveformrraudio_effector waveform_augrrr apply_codec3szCodecAugment.apply_codeccCs t|j\}}|j|||dS)a> Apply a random audio codec from the available list. Arguments --------- waveform: torch.Tensor Input waveform of shape `[batch, time]`. Returns ------- torch.Tensor Coded version of the input waveform of shape `[batch, time]`. r)randomchoicer r )r rrrrrrforwardMszCodecAugment.forward)r)NN)__name__ __module__ __qualname____doc__r r r# __classcell__rrr rrs  r)r'r!torchrnnModulerrrrrs