o j@sPddlmZmZddlmZddlmZddlmZm Z eGdddeZ dS)) dataclassfield)List) BaseTTSConfig)VitsArgsVitsAudioConfigc@s4eZdZUdZdZeed<eedZ eed<ee dZ e ed<edddZ e eed <d Zeed <d Zeed <d Zeed<edddZeed<d Zeed<edddZeed<dZeed<dZeed<edddZeed<dZeed<dZeed<dZeed<dZeed<dZeed <dZeed!<dZ eed"<dZ!eed#<dZ"eed$<d%Z#eed&<ed'ddZ$eed(<ed)ddZ%eed*<d+Z&e'ed,<dZ(eed-<ed.ddZ)e e ed/<d0Z*e'ed1<d%Z+eed2<d3Z,eed4<d5Z-e'ed6<d3Z.eed7<d%Z/eed8<d%Z0eed9<d3Z1e eed:<d3Z2e'ed;<d VitsConfigadDefines parameters for VITS End2End TTS model. Args: model (str): Model name. Do not change unless you know what you are doing. model_args (VitsArgs): Model architecture arguments. Defaults to `VitsArgs()`. audio (VitsAudioConfig): Audio processing configuration. Defaults to `VitsAudioConfig()`. grad_clip (List): Gradient clipping thresholds for each optimizer. Defaults to `[1000.0, 1000.0]`. lr_gen (float): Initial learning rate for the generator. Defaults to 0.0002. lr_disc (float): Initial learning rate for the discriminator. Defaults to 0.0002. lr_scheduler_gen (str): Name of the learning rate scheduler for the generator. One of the `torch.optim.lr_scheduler.*`. Defaults to `ExponentialLR`. lr_scheduler_gen_params (dict): Parameters for the learning rate scheduler of the generator. Defaults to `{'gamma': 0.999875, "last_epoch":-1}`. lr_scheduler_disc (str): Name of the learning rate scheduler for the discriminator. One of the `torch.optim.lr_scheduler.*`. Defaults to `ExponentialLR`. lr_scheduler_disc_params (dict): Parameters for the learning rate scheduler of the discriminator. Defaults to `{'gamma': 0.999875, "last_epoch":-1}`. scheduler_after_epoch (bool): If true, step the schedulers after each epoch else after each step. Defaults to `False`. optimizer (str): Name of the optimizer to use with both the generator and the discriminator networks. One of the `torch.optim.*`. Defaults to `AdamW`. kl_loss_alpha (float): Loss weight for KL loss. Defaults to 1.0. disc_loss_alpha (float): Loss weight for the discriminator loss. Defaults to 1.0. gen_loss_alpha (float): Loss weight for the generator loss. Defaults to 1.0. feat_loss_alpha (float): Loss weight for the feature matching loss. Defaults to 1.0. mel_loss_alpha (float): Loss weight for the mel loss. Defaults to 45.0. return_wav (bool): If true, data loader returns the waveform as well as the other outputs. Do not change. Defaults to `True`. compute_linear_spec (bool): If true, the linear spectrogram is computed and returned alongside the mel output. Do not change. Defaults to `True`. use_weighted_sampler (bool): If true, use weighted sampler with bucketing for balancing samples between datasets used in training. Defaults to `False`. weighted_sampler_attrs (dict): Key retuned by the formatter to be used for weighted sampler. For example `{"root_path": 2.0, "speaker_name": 1.0}` sets sample probabilities by overweighting `root_path` by 2.0. Defaults to `{}`. weighted_sampler_multipliers (dict): Weight each unique value of a key returned by the formatter for weighted sampling. For example `{"root_path":{"/raid/datasets/libritts-clean-16khz-bwe-coqui_44khz/LibriTTS/train-clean-100/":1.0, "/raid/datasets/libritts-clean-16khz-bwe-coqui_44khz/LibriTTS/train-clean-360/": 0.5}`. It will sample instances from `train-clean-100` 2 times more than `train-clean-360`. Defaults to `{}`. r (int): Number of spectrogram frames to be generated at a time. Do not change. Defaults to `1`. add_blank (bool): If true, a blank token is added in between every character. Defaults to `True`. test_sentences (List[List]): List of sentences with speaker and language information to be used for testing. language_ids_file (str): Path to the language ids file. use_language_embedding (bool): If true, language embedding is used. Defaults to `False`. Note: Check :class:`TTS.tts.configs.shared_configs.BaseTTSConfig` for the inherited parameters. Example: >>> from TTS.tts.configs.vits_config import VitsConfig >>> config = VitsConfig() vitsmodel)default_factory model_argsaudiocCsddgS)NirrrN/home/kuhnn/.local/lib/python3.10/site-packages/TTS/tts/configs/vits_config.pysszVitsConfig. grad_clipg-C6*?lr_genlr_disc ExponentialLRlr_scheduler_gencC dddSNg"?)gamma last_epochrrrrrrw lr_scheduler_gen_paramslr_scheduler_disccCrrrrrrrryrlr_scheduler_disc_paramsTscheduler_after_epochAdamW optimizercCsddgdddS)Ng?gGz?g& .>g{Gz?)betaseps weight_decayrrrrrr|soptimizer_paramsg? kl_loss_alphadisc_loss_alphagen_loss_alphafeat_loss_alphagF@mel_loss_alphadur_loss_alphaspeaker_encoder_loss_alpha return_wavcompute_linear_specFuse_weighted_samplercCiSNrrrrrrweighted_sampler_attrscCr0r1rrrrrrr2weighted_sampler_multipliersr add_blankcCsdgdgdgdgdggS)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_sentencesr num_speakersuse_speaker_embeddingN speakers_filespeaker_embedding_channelslanguage_ids_fileuse_language_embeddinguse_d_vector_file d_vector_file d_vector_dimcCs*|jD] \}}t||r|||<qdSr1)r itemshasattr)selfkeyvalrrr __post_init__s  zVitsConfig.__post_init__)4__name__ __module__ __qualname____doc__r str__annotations__rrr rr rrfloatrrrrdictrrrboolr!r%r&r'r(r)r*r+r,r-r.r/r3r4r6intr7r8r9r:r;r=r>r?r@rArBrHrrrrrsT  c                          rN) dataclassesrrtypingrTTS.tts.configs.shared_configsrTTS.tts.models.vitsrrrrrrrs