ukrainian-tts / config.json
Yurii Paniv
Add version 3.0.0
a163565
{
"output_path": "/home/robinhad/Projects/TTS",
"logger_uri": null,
"run_name": "vits_mykyta_latest",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 25,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"log_model_step": 5000,
"save_step": 5000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 10000,
"target_loss": null,
"print_eval": false,
"test_delay_epochs": -1,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": true,
"epochs": 1500,
"batch_size": 64,
"eval_batch_size": 16,
"grad_clip": [
1000,
1000
],
"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": "",
"lr_scheduler_params": {},
"use_grad_scaler": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "vits",
"num_loader_workers": 12,
"num_eval_loader_workers": 12,
"use_noise_augment": false,
"audio": {
"fft_size": 1024,
"win_length": 1024,
"hop_length": 256,
"frame_shift_ms": null,
"frame_length_ms": null,
"stft_pad_mode": "reflect",
"sample_rate": 22050,
"resample": false,
"preemphasis": 0,
"ref_level_db": 35,
"do_sound_norm": true,
"log_func": "np.log",
"do_trim_silence": false,
"trim_db": 35,
"do_rms_norm": false,
"db_level": -24,
"power": 1.1,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 0,
"mel_fmax": null,
"spec_gain": 6.0,
"do_amp_to_db_linear": true,
"do_amp_to_db_mel": true,
"pitch_fmax": 640.0,
"pitch_fmin": 0.0,
"signal_norm": true,
"min_level_db": -100,
"symmetric_norm": true,
"max_norm": 1.0,
"clip_norm": true,
"stats_path": null
},
"use_phonemes": false,
"phonemizer": null,
"phoneme_language": "uk",
"compute_input_seq_cache": false,
"text_cleaner": "basic_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": "/home/robinhad/Projects/TTS/phoneme_cache",
"characters": {
"characters_class": "TTS.tts.models.vits.VitsCharacters",
"vocab_dict": null,
"pad": "<PAD>",
"eos": "<EOS>",
"bos": "<BOS>",
"blank": "<BLNK>",
"characters": "!\"'(),-/:;.?\u00ab\u00bb+\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\u044c\u044e\u044f\u0454\u0456\u0457\u0491\u2013\u2014\u2015\u2018\u2019\u201c\u201d\u201e\u2026 ",
"punctuations": "!\"'(),-/:;?\u00ab\u00bb+\u2013\u2014\u2015\u2018\u2019\u201c\u201d\u201e\u2026 ",
"phonemes": null,
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"batch_group_size": 0,
"loss_masking": null,
"sort_by_audio_len": true,
"min_audio_len": 32768,
"max_audio_len": 264600,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_linear_spec": true,
"precompute_num_workers": 16,
"start_by_longest": false,
"datasets": [
{
"name": "mailabs",
"path": "/home/robinhad/Data/Audio/ukr-tts-dataset-mai",
"meta_file_train": "",
"ignored_speakers": null,
"language": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
[
"\u0414+\u0435\u0441\u044f\u0442\u044c \u0440\u0430\u0437+\u0456\u0432 \u0432\u0456\u0434\u043c+\u0456\u0440\u044f\u0439, +\u0430 \u0440+\u0430\u0437 - \u0432\u0456\u0434\u0440+\u0456\u0436.",
"olena",
null,
null
],
[
"\u0413\u043e\u0432\u043e\u0440+\u0438, \u043d+\u0456\u0431\u0438 \u0442+\u0438 \u0436\u0438\u0432+\u0438\u0439!"
],
[
"\u041f\u0435\u0440\u0435\u043f\u0440+\u043e\u0448\u0443\u044e, \u0414+\u0435\u0439\u0432\u0435, \u043d+\u0430 \u0436+\u0430\u043b\u044c, +\u044f \u043d+\u0435 \u043c+\u043e\u0436\u0443 \u0437\u0440\u043e\u0431+\u0438\u0442\u0438 \u0446+\u0435.",
"lada",
null,
null
],
[
"\u041f\u0435\u0440\u0435\u043f\u0440+\u043e\u0448\u0443\u044e, \u0414+\u0435\u0439\u0432\u0435, \u043d+\u0430 \u0436+\u0430\u043b\u044c, +\u044f \u043d+\u0435 \u043c+\u043e\u0436\u0443 \u0437\u0440\u043e\u0431+\u0438\u0442\u0438 \u0446+\u0435.",
"mykyta",
null,
null
],
[
"\u0425\u0442+\u043e \u0442+\u0438 \u0442\u0430\u043a+\u0438\u0439 +\u0456 +\u044f\u043a \u0442\u0435\u0431+\u0435 \u0437\u0432+\u0430\u0442\u0438?",
"mykyta",
null,
null
],
[
"\u0425\u0442+\u043e \u0442+\u0438 \u0442\u0430\u043a+\u0438\u0439 +\u0456 +\u044f\u043a \u0442\u0435\u0431+\u0435 \u0437\u0432+\u0430\u0442\u0438?",
"dmytro",
null,
null
],
[
"\u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u0438\u0439 - \u043c+\u0456\u0441\u0442\u043e \u0432 \u0425\u043c\u0435\u043b\u044c\u043d+\u0438\u0446\u044c\u043a\u0456\u0439 +\u043e\u0431\u043b\u0430\u0441\u0442\u0456 \u0423\u043a\u0440\u0430+\u0457\u043d\u0438, \u0446+\u0435\u043d\u0442\u0440 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0457 \u043c\u0456\u0441\u044c\u043a+\u043e\u0457 \u043e\u0431'+\u0454\u0434\u043d\u0430\u043d\u043e\u0457 \u0442\u0435\u0440\u0438\u0442\u043e\u0440\u0456+\u0430\u043b\u044c\u043d\u043e\u0457 \u0433\u0440\u043e\u043c+\u0430\u0434\u0438 +\u0456 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0433\u043e \u0440\u0430\u0439+\u043e\u043d\u0443.",
"lada",
null,
null
],
[
"\u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u0438\u0439 - \u043c+\u0456\u0441\u0442\u043e \u0432 \u0425\u043c\u0435\u043b\u044c\u043d+\u0438\u0446\u044c\u043a\u0456\u0439 +\u043e\u0431\u043b\u0430\u0441\u0442\u0456 \u0423\u043a\u0440\u0430+\u0457\u043d\u0438, \u0446+\u0435\u043d\u0442\u0440 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0457 \u043c\u0456\u0441\u044c\u043a+\u043e\u0457 \u043e\u0431'+\u0454\u0434\u043d\u0430\u043d\u043e\u0457 \u0442\u0435\u0440\u0438\u0442\u043e\u0440\u0456+\u0430\u043b\u044c\u043d\u043e\u0457 \u0433\u0440\u043e\u043c+\u0430\u0434\u0438 +\u0456 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0433\u043e \u0440\u0430\u0439+\u043e\u043d\u0443.",
"dmytro",
null,
null
],
[
"\u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u0438\u0439 - \u043c+\u0456\u0441\u0442\u043e \u0432 \u0425\u043c\u0435\u043b\u044c\u043d+\u0438\u0446\u044c\u043a\u0456\u0439 +\u043e\u0431\u043b\u0430\u0441\u0442\u0456 \u0423\u043a\u0440\u0430+\u0457\u043d\u0438, \u0446+\u0435\u043d\u0442\u0440 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0457 \u043c\u0456\u0441\u044c\u043a+\u043e\u0457 \u043e\u0431'+\u0454\u0434\u043d\u0430\u043d\u043e\u0457 \u0442\u0435\u0440\u0438\u0442\u043e\u0440\u0456+\u0430\u043b\u044c\u043d\u043e\u0457 \u0433\u0440\u043e\u043c+\u0430\u0434\u0438 +\u0456 \u041a\u0430\u043c'\u044f\u043d+\u0435\u0446\u044c-\u041f\u043e\u0434+\u0456\u043b\u044c\u0441\u044c\u043a\u043e\u0433\u043e \u0440\u0430\u0439+\u043e\u043d\u0443.",
"olga",
null,
null
]
],
"eval_split_max_size": null,
"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": 84,
"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": 6,
"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": "1",
"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,
"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": true,
"num_speakers": 5,
"speakers_file": "speakers.pth",
"d_vector_file": null,
"speaker_embedding_channels": 256,
"use_d_vector_file": false,
"d_vector_dim": 0,
"detach_dp_input": true,
"use_language_embedding": false,
"embedded_language_dim": 4,
"num_languages": 0,
"language_ids_file": null,
"use_speaker_encoder_as_loss": false,
"speaker_encoder_config_path": "",
"speaker_encoder_model_path": "",
"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": 1.0,
"return_wav": true,
"r": 1,
"num_speakers": 0,
"use_speaker_embedding": true,
"speakers_file": "speakers.pth",
"speaker_embedding_channels": 256,
"language_ids_file": null,
"use_language_embedding": false,
"use_d_vector_file": false,
"d_vector_file": null,
"d_vector_dim": 0
}