o j @sddlZddlmZddlmZmZddlZddlZddl m Z ddl TdZ ddee eejfdeefd d Zd d ZdddZdS)N)Path)OptionalUnion)binary_dilation)*i fpath_or_wav source_srcCsdt|ts t|trtj|dd\}}n|}|dur%|tkr%t||t}t|tdd}t |}|S)a Applies the preprocessing operations used in training the Speaker Encoder to a waveform either on disk or in memory. The waveform will be resampled to match the data hyperparameters. :param fpath_or_wav: either a filepath to an audio file (many extensions are supported, not just .wav), either the waveform as a numpy array of floats. :param source_sr: if passing an audio waveform, the sampling rate of the waveform before preprocessing. After preprocessing, the waveform's sampling rate will match the data hyperparameters. If passing a filepath, the sampling rate will be automatically detected and this argument will be ignored. N)srT) increase_only) isinstancestrrlibrosaload sampling_rateresamplenormalize_volumeaudio_norm_target_dBFStrim_long_silences)rrwavr^/home/kuhnn/.local/lib/python3.10/site-packages/TTS/vc/modules/freevc/speaker_encoder/audio.pypreprocess_wavs rcCs<tjj|ttttdtttdtd}|t j j S)z Derives a mel spectrogram ready to be used by the encoder from a preprocessed audio waveform. Note: this not a log-mel spectrogram. i)yr n_fft hop_lengthn_mels) r featuremelspectrogramrintmel_window_lengthmel_window_stepmel_n_channelsastypenpfloat32T)rframesrrrwav_to_mel_spectrogram,sr'FcCsX|r|rtd|dtt|d}|dkr|s"|dkr$|r$|S|d|dS)Nz,Both increase only and decrease only are set r) ValueErrorr#log10mean)r target_dBFSr decrease_only dBFS_changerrrr;s r)N)FF)structpathlibrtypingrrr numpyr#scipy.ndimage.morphologyr-TTS.vc.modules.freevc.speaker_encoder.hparams int16_maxr ndarrayrrr'rrrrrs  $