o j@sTddlmZmZddlmZddlmZddlmZm Z m Z eGdddeZ dS)) dataclassfield)List) BaseTTSConfig)DelightfulTtsArgsDelightfulTtsAudioConfig VocoderConfigc@seZdZUdZdZeed<eedZ eed<ee dZ e ed<dZ e ed<eedZeed <dZe ed <d Zeed <ed ddZeeed<dZeed<dZeed<dZeed<edddZeed<dZeed<edddZeed<dZe ed<dZeed<edddZeed<dZ eed <dZ!eed!<dZ"eed"<dZ#eed#<dZ$eed$<d%Z%eed&<d%Z&eed'<dZ'eed(<d)Z(eed*<d+Z)eed,<d-Z*eed.<dZ+eed/<dZ,eed0<dZ-eed1<d2Z.eed3<d4Z/eed5<ed6ddZ0eed7<dZ1e ed8<d9Z2e ed:<ed;ddZ3eed<<ed=ddZ4eed><d?Z5eed@<dZ6e edA<dBZ7eedC<dBZ8eedD<dEZ9eedF<d9Z:e edG<dBZ;eedH<dIZe edL<d9Z?e edM<dBZ@eedN<dBZAeedO<edPddZBeeeedQ<dRdSZCdBS)TDelightfulTTSConfiga Configuration class for the DelightfulTTS model. Attributes: model (str): Name of the model ("delightful_tts"). audio (DelightfulTtsAudioConfig): Configuration for audio settings. model_args (DelightfulTtsArgs): Configuration for model arguments. use_attn_priors (bool): Whether to use attention priors. vocoder (VocoderConfig): Configuration for the vocoder. init_discriminator (bool): Whether to initialize the discriminator. steps_to_start_discriminator (int): Number of steps to start the discriminator. grad_clip (List[float]): Gradient clipping values. lr_gen (float): Learning rate for the gan generator. lr_disc (float): Learning rate for the gan discriminator. lr_scheduler_gen (str): Name of the learning rate scheduler for the generator. lr_scheduler_gen_params (dict): Parameters for the learning rate scheduler for the generator. lr_scheduler_disc (str): Name of the learning rate scheduler for the discriminator. lr_scheduler_disc_params (dict): Parameters for the learning rate scheduler for the discriminator. scheduler_after_epoch (bool): Whether to schedule after each epoch. optimizer (str): Name of the optimizer. optimizer_params (dict): Parameters for the optimizer. ssim_loss_alpha (float): Alpha value for the SSIM loss. mel_loss_alpha (float): Alpha value for the mel loss. aligner_loss_alpha (float): Alpha value for the aligner loss. pitch_loss_alpha (float): Alpha value for the pitch loss. energy_loss_alpha (float): Alpha value for the energy loss. u_prosody_loss_alpha (float): Alpha value for the utterance prosody loss. p_prosody_loss_alpha (float): Alpha value for the phoneme prosody loss. dur_loss_alpha (float): Alpha value for the duration loss. char_dur_loss_alpha (float): Alpha value for the character duration loss. binary_align_loss_alpha (float): Alpha value for the binary alignment loss. binary_loss_warmup_epochs (int): Number of warm-up epochs for the binary loss. disc_loss_alpha (float): Alpha value for the discriminator loss. gen_loss_alpha (float): Alpha value for the generator loss. feat_loss_alpha (float): Alpha value for the feature loss. vocoder_mel_loss_alpha (float): Alpha value for the vocoder mel loss. multi_scale_stft_loss_alpha (float): Alpha value for the multi-scale STFT loss. multi_scale_stft_loss_params (dict): Parameters for the multi-scale STFT loss. return_wav (bool): Whether to return audio waveforms. use_weighted_sampler (bool): Whether to use a weighted sampler. weighted_sampler_attrs (dict): Attributes for the weighted sampler. weighted_sampler_multipliers (dict): Multipliers for the weighted sampler. r (int): Value for the `r` override. compute_f0 (bool): Whether to compute F0 values. f0_cache_path (str): Path to the F0 cache. attn_prior_cache_path (str): Path to the attention prior cache. num_speakers (int): Number of speakers. use_speaker_embedding (bool): Whether to use speaker embedding. speakers_file (str): Path to the speaker file. speaker_embedding_channels (int): Number of channels for the speaker embedding. language_ids_file (str): Path to the language IDs file. delightful_ttsmodel)default_factoryaudio model_argsTuse_attn_priorsvocoderinit_discriminatori@ steps_to_start_discriminatorcCsddgS)NirrrX/home/kuhnn/.local/lib/python3.10/site-packages/TTS/tts/configs/delightful_tts_config.pyLszDelightfulTTSConfig. grad_clipg-C6*?lr_genlr_disc ExponentialLRlr_scheduler_gencC dddSNg"?)gamma last_epochrrrrrrP lr_scheduler_gen_paramslr_scheduler_disccCrrrrrrrrRr lr_scheduler_disc_paramsscheduler_after_epochAdamW optimizercCsddgdddS)Ng?gGz?g& .>{Gz?)betaseps weight_decayrrrrrrUsoptimizer_paramsg?ssim_loss_alphamel_loss_alphaaligner_loss_alphapitch_loss_alphaenergy_loss_alphag?u_prosody_loss_alphap_prosody_loss_alphadur_loss_alphar'char_dur_loss_alphag?binary_align_loss_alpha binary_loss_warmup_epochsdisc_loss_alphagen_loss_alphafeat_loss_alphag$@vocoder_mel_loss_alphag@multi_scale_stft_loss_alphacCsgdgdgddS)N)iii)x2)iXir>)n_ffts hop_lengths win_lengthsrrrrrrksmulti_scale_stft_loss_params return_wavFuse_weighted_samplercCiSNrrrrrruweighted_sampler_attrscCrFrGrrrrrrvrHweighted_sampler_multipliersr compute_f0N f0_cache_pathattn_prior_cache_pathr num_speakersuse_speaker_embedding speakers_filespeaker_embedding_channelslanguage_ids_fileuse_language_embeddinguse_d_vector_file d_vector_file d_vector_dimcCsdgdgdgdgdggS)NzcIt took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.zBe a voice, not an echo.z+I'm sorry Dave. I'm afraid I can't do that.z0This cake is great. It's so delicious and moist.zPrior to November 22, 1963.rrrrrrs test_sentencescCsv|jdkr |j|j_|jrd|j_|jr|j|j_|jr d|j_|jdur/|jdkr/|j|j_|jr9|j|j_dSdS)NrT)rPrrQrRrWrYrX)selfrrr __post_init__s    z!DelightfulTTSConfig.__post_init__)D__name__ __module__ __qualname____doc__r str__annotations__rrr rrrboolrrrrintrrfloatrrrr!dictr"r#r$r&r+r,r-r.r/r0r1r2r3r4r5r7r8r9r:r;r<rCrDrErIrJrLrMrNrOrPrQrRrTrUrVrWrXrYrZr\rrrrr sv  5                                        r N) dataclassesrrtypingrTTS.tts.configs.shared_configsrTTS.tts.models.delightful_ttsrrrr rrrrs