jvision's picture
First commit
f00d951
raw
history blame
8.56 kB
{
"logger_uri": null,
"run_name": "VCTK_European_English_Males",
"project_name": "YourTTS",
"run_description": "\n - Original YourTTS trained using VCTK dataset\n ",
"print_step": 50,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"save_on_interrupt": true,
"log_model_step": 1000,
"save_step": 5000,
"save_n_checkpoints": 2,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 10000,
"target_loss": "loss_1",
"print_eval": false,
"test_delay_epochs": 0,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": true,
"epochs": 1000,
"batch_size": 16,
"eval_batch_size": 16,
"grad_clip": [
1000.0,
1000.0
],
"scheduler_after_epoch": true,
"lr": 0.001,
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"weight_decay": 0.01
},
"lr_scheduler": null,
"lr_scheduler_params": {},
"use_grad_scaler": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "vits",
"num_loader_workers": 8,
"num_eval_loader_workers": 0,
"use_noise_augment": false,
"audio": {
"fft_size": 1024,
"sample_rate": 16000,
"win_length": 1024,
"hop_length": 256,
"num_mels": 80,
"mel_fmin": 0,
"mel_fmax": null
},
"use_phonemes": false,
"phonemizer": "espeak",
"phoneme_language": "en-us",
"compute_input_seq_cache": true,
"text_cleaner": "multilingual_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": "projects/art/phoneme_cache",
"characters": {
"characters_class": "TTS.tts.models.vits.VitsCharacters",
"vocab_dict": null,
"pad": "_",
"eos": "&",
"bos": "*",
"blank": null,
"characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u00af\u00b7\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f9\u00fa\u00fb\u00fc\u00ff\u0101\u0105\u0107\u0113\u0119\u011b\u012b\u0131\u0142\u0144\u014d\u0151\u0153\u015b\u016b\u0171\u017a\u017c\u01ce\u01d0\u01d2\u01d4\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0454\u0456\u0457\u0491\u2013!'(),-.:;? ",
"punctuations": "!'(),-.:;? ",
"phonemes": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u025a\u02de\u026b'\u0303' ",
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"batch_group_size": 48,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": 160000,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": true,
"precompute_num_workers": 12,
"start_by_longest": true,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "vctk",
"language": "en"
}
],
"test_sentences": [
[
"This is an example of a sentence to be synthesized.",
"VCTK_p226",
null,
"en"
],
[
"This is an example of a sentence to be synthesized.",
"VCTK_p227",
null,
"en"
]
],
"eval_split_max_size": 256,
"eval_split_size": 0.01,
"use_speaker_weighted_sampler": false,
"speaker_weighted_sampler_alpha": 1.0,
"use_language_weighted_sampler": false,
"language_weighted_sampler_alpha": 1.0,
"use_length_weighted_sampler": false,
"length_weighted_sampler_alpha": 1.0,
"model_args": {
"num_chars": 284,
"out_channels": 513,
"spec_segment_size": 32,
"hidden_channels": 192,
"hidden_channels_ffn_text_encoder": 768,
"num_heads_text_encoder": 2,
"num_layers_text_encoder": 10,
"kernel_size_text_encoder": 3,
"dropout_p_text_encoder": 0.1,
"dropout_p_duration_predictor": 0.5,
"kernel_size_posterior_encoder": 5,
"dilation_rate_posterior_encoder": 1,
"num_layers_posterior_encoder": 16,
"kernel_size_flow": 5,
"dilation_rate_flow": 1,
"num_layers_flow": 4,
"resblock_type_decoder": "2",
"resblock_kernel_sizes_decoder": [
3,
7,
11
],
"resblock_dilation_sizes_decoder": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"upsample_rates_decoder": [
8,
8,
2,
2
],
"upsample_initial_channel_decoder": 512,
"upsample_kernel_sizes_decoder": [
16,
16,
4,
4
],
"periods_multi_period_discriminator": [
2,
3,
5,
7,
11
],
"use_sdp": true,
"noise_scale": 1.0,
"inference_noise_scale": 0.667,
"length_scale": 1.0,
"noise_scale_dp": 1.0,
"inference_noise_scale_dp": 1.0,
"max_inference_len": null,
"init_discriminator": true,
"use_spectral_norm_disriminator": false,
"use_speaker_embedding": false,
"num_speakers": 21,
"speakers_file": "supplemental/speakers.pth",
"d_vector_file": [
"supplemental/speakers-base.json",
"supplemental/speakers-dataset.pth"
],
"speaker_embedding_channels": 256,
"use_d_vector_file": true,
"d_vector_dim": 512,
"detach_dp_input": true,
"use_language_embedding": true,
"embedded_language_dim": 4,
"num_languages": 3,
"language_ids_file": "supplemental/language_ids.json",
"use_speaker_encoder_as_loss": true,
"speaker_encoder_config_path": "supplemental/config_se.json",
"speaker_encoder_model_path": "supplemental/model_se.pth.tar",
"condition_dp_on_speaker": true,
"freeze_encoder": false,
"freeze_DP": false,
"freeze_PE": false,
"freeze_flow_decoder": false,
"freeze_waveform_decoder": false,
"encoder_sample_rate": null,
"interpolate_z": true,
"reinit_DP": false,
"reinit_text_encoder": false
},
"lr_gen": 0.0002,
"lr_disc": 0.0002,
"lr_scheduler_gen": "ExponentialLR",
"lr_scheduler_gen_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"lr_scheduler_disc": "ExponentialLR",
"lr_scheduler_disc_params": {
"gamma": 0.999875,
"last_epoch": -1
},
"kl_loss_alpha": 1.0,
"disc_loss_alpha": 1.0,
"gen_loss_alpha": 1.0,
"feat_loss_alpha": 1.0,
"mel_loss_alpha": 45.0,
"dur_loss_alpha": 1.0,
"speaker_encoder_loss_alpha": 9.0,
"return_wav": true,
"use_weighted_sampler": false,
"weighted_sampler_attrs": {},
"weighted_sampler_multipliers": {},
"r": 1,
"num_speakers": 21,
"use_speaker_embedding": false,
"speakers_file": "supplemental/speakers.pth",
"speaker_embedding_channels": 256,
"language_ids_file": "supplemental/language_ids.json",
"use_language_embedding": true,
"use_d_vector_file": true,
"d_vector_file": [
"supplemental/speakers-base.json",
"supplemental/speakers-dataset.pth"
],
"d_vector_dim": 512
}