o jy&@sxddlmZmZddlmZddlmZmZddlm Z eGdddeZ eGdddeZ eGd d d e Z d S) )asdict dataclass)List)Coqpitcheck_argument) TrainerConfigc@seZdZUdZdZeed<dZeed<dZeed<dZ eed<dZ eed <d Z e ed <d Z eed <dZeed<dZeed<dZeed<dZeed<dZe ed<dZeed<dZeed<dZeed<dZeed<dZeed<dZeed <d!Zeed"<dZeed#<dZeed$<dZeed%<dZeed&<dZ eed'<d(Z!eed)<d*Z"eed+<dZ#eed,<d-Z$eed.<dZ%eed/<d0Z&eed1<dZ'eed2<dZ(e ed3<d4d5Z)dS)6BaseAudioConfigamBase config to definge audio processing parameters. It is used to initialize ```TTS.utils.audio.AudioProcessor.``` Args: fft_size (int): Number of STFT frequency levels aka.size of the linear spectogram frame. Defaults to 1024. win_length (int): Each frame of audio is windowed by window of length ```win_length``` and then padded with zeros to match ```fft_size```. Defaults to 1024. hop_length (int): Number of audio samples between adjacent STFT columns. Defaults to 1024. frame_shift_ms (int): Set ```hop_length``` based on milliseconds and sampling rate. frame_length_ms (int): Set ```win_length``` based on milliseconds and sampling rate. stft_pad_mode (str): Padding method used in STFT. 'reflect' or 'center'. Defaults to 'reflect'. sample_rate (int): Audio sampling rate. Defaults to 22050. resample (bool): Enable / Disable resampling audio to ```sample_rate```. Defaults to ```False```. preemphasis (float): Preemphasis coefficient. Defaults to 0.0. ref_level_db (int): 20 Reference Db level to rebase the audio signal and ignore the level below. 20Db is assumed the sound of air. Defaults to 20. do_sound_norm (bool): Enable / Disable sound normalization to reconcile the volume differences among samples. Defaults to False. log_func (str): Numpy log function used for amplitude to DB conversion. Defaults to 'np.log10'. do_trim_silence (bool): Enable / Disable trimming silences at the beginning and the end of the audio clip. Defaults to ```True```. do_amp_to_db_linear (bool, optional): enable/disable amplitude to dB conversion of linear spectrograms. Defaults to True. do_amp_to_db_mel (bool, optional): enable/disable amplitude to dB conversion of mel spectrograms. Defaults to True. pitch_fmax (float, optional): Maximum frequency of the F0 frames. Defaults to ```640```. pitch_fmin (float, optional): Minimum frequency of the F0 frames. Defaults to ```1```. trim_db (int): Silence threshold used for silence trimming. Defaults to 45. do_rms_norm (bool, optional): enable/disable RMS volume normalization when loading an audio file. Defaults to False. db_level (int, optional): dB level used for rms normalization. The range is -99 to 0. Defaults to None. power (float): Exponent used for expanding spectrogra levels before running Griffin Lim. It helps to reduce the artifacts in the synthesized voice. Defaults to 1.5. griffin_lim_iters (int): Number of Griffing Lim iterations. Defaults to 60. num_mels (int): Number of mel-basis frames that defines the frame lengths of each mel-spectrogram frame. Defaults to 80. mel_fmin (float): Min frequency level used for the mel-basis filters. ~50 for male and ~95 for female voices. It needs to be adjusted for a dataset. Defaults to 0. mel_fmax (float): Max frequency level used for the mel-basis filters. It needs to be adjusted for a dataset. spec_gain (int): Gain applied when converting amplitude to DB. Defaults to 20. signal_norm (bool): enable/disable signal normalization. Defaults to True. min_level_db (int): minimum db threshold for the computed melspectrograms. Defaults to -100. symmetric_norm (bool): enable/disable symmetric normalization. If set True normalization is performed in the range [-k, k] else [0, k], Defaults to True. max_norm (float): ```k``` defining the normalization range. Defaults to 4.0. clip_norm (bool): enable/disable clipping the our of range values in the normalized audio signal. Defaults to True. stats_path (str): Path to the computed stats file. Defaults to None. ifft_size win_length hop_lengthNframe_shift_msframe_length_msreflect stft_pad_modei"V sample_rateFresample preemphasis ref_level_db do_sound_normznp.log10log_funcTdo_trim_silence-trim_db do_rms_normdb_levelg?power<griffin_lim_itersPnum_melsmel_fminmel_fmax spec_gaindo_amp_to_db_lineardo_amp_to_db_melg@ pitch_fmaxg? pitch_fmin signal_normi min_level_dbsymmetric_normg@max_norm clip_norm stats_pathcCsRt|}td|ddddtd|ddddtd |dd d dtd |ddd ddtd|ddd ddtd|ddddtd|ddddtd|ddd dtd|ddddtd|ddd dtd|ddtd|ddtd|ddd dtd |ddtd!|dd"d dtd#|dd$dd%td&|ddd'dtd(|ddtd)|ddd*S)+Check config fieldsr"T i) restrictedmin_valmax_valr iriirir )r2r3r4 alternativer r rrr+irrr r*r2r,r-g?r.r#rr$g@@)r2r3 allow_noner%drrNrrselfcr@L/home/kuhnn/.local/lib/python3.10/site-packages/TTS/config/shared_configs.py check_valuess6zBaseAudioConfig.check_values)*__name__ __module__ __qualname____doc__r int__annotations__r r r rrstrrrboolrfloatrrrrrrrrr r"r#r$r%r&r'r(r)r*r+r,r-r.r/rBr@r@r@rArsF  j                                rc@seZdZUdZdZeed<dZeed<dZeed<dZ eed<dZ e eed<dZ eed <dZ eed <dZeed <dZeed <d dZdS)BaseDatasetConfigaBase config for TTS datasets. Args: formatter (str): Formatter name that defines used formatter in ```TTS.tts.datasets.formatter```. Defaults to `""`. dataset_name (str): Unique name for the dataset. Defaults to `""`. path (str): Root path to the dataset files. Defaults to `""`. meta_file_train (str): Name of the dataset meta file. Or a list of speakers to be ignored at training for multi-speaker datasets. Defaults to `""`. ignored_speakers (List): List of speakers IDs that are not used at the training. Default None. language (str): Language code of the dataset. If defined, it overrides `phoneme_language`. Defaults to `""`. phonemizer (str): Phonemizer used for that dataset's language. By default it uses `DEF_LANG_TO_PHONEMIZER`. Defaults to `""`. meta_file_val (str): Name of the dataset meta file that defines the instances used at validation. meta_file_attn_mask (str): Path to the file that lists the attention mask files used with models that require attention masks to train the duration predictor. formatter dataset_namepathmeta_file_trainNignored_speakerslanguage phonemizer meta_file_valmeta_file_attn_maskcCsRt|}td|ddtd|ddtd|ddtd|ddtd|ddd S) r0rNTr9rPrQrUFrVNr<r=r@r@rArBs zBaseDatasetConfig.check_values)rCrDrErFrNrIrHrOrPrQrRrrSrTrUrVrBr@r@r@rArLs  !        rLc@sBeZdZUdZdZeed<dZeed<dZ eed<dZ e ed<dS) BaseTrainingConfiguBase config to define the basic 🐸TTS training parameters that are shared among all the models. It is based on ```Trainer.TrainingConfig```. Args: model (str): Name of the model that is used in the training. num_loader_workers (int): Number of workers for training time dataloader. num_eval_loader_workers (int): Number of workers for evaluation time dataloader. Nmodelrnum_loader_workersnum_eval_loader_workersFuse_noise_augment) rCrDrErFrXrIrHrYrGrZr[rJr@r@r@rArWs    rWN) dataclassesrrtypingrcoqpitrrtrainerrrrLrWr@r@r@rAs  78