Voice-Cloning / config.json
Kevin676's picture
Duplicate from BilalSardar/Voice-Cloning
1820ca7
raw
history blame
12.3 kB
{
"model": "vits",
"run_name": "vits_tts-portuguese",
"run_description": "",
"epochs": 1000,
"batch_size": 52,
"eval_batch_size": 52,
"mixed_precision": false,
"scheduler_after_epoch": true,
"run_eval": true,
"test_delay_epochs": -1,
"print_eval": true,
"dashboard_logger": "tensorboard",
"print_step": 25,
"plot_step": 100,
"model_param_stats": false,
"project_name": null,
"log_model_step": 10000,
"wandb_entity": null,
"save_step": 10000,
"checkpoint": true,
"keep_all_best": false,
"keep_after": 10000,
"num_loader_workers": 4,
"num_eval_loader_workers": 4,
"use_noise_augment": false,
"use_language_weighted_sampler": true,
"output_path": "../checkpoints/VITS-multilingual/VITS_fixes/new/new-SE/use_noise_aument_false/xlarge-ZS-PT-VCTK/pt-en+LibriTTS-fr/speaker_encoder_as_loss_9_alpha/mixed-p-false-bug-SDP-fixed/",
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"audio": {
"fft_size": 1024,
"win_length": 1024,
"hop_length": 256,
"frame_shift_ms": null,
"frame_length_ms": null,
"stft_pad_mode": "reflect",
"sample_rate": 16000,
"resample": false,
"preemphasis": 0.0,
"ref_level_db": 20,
"do_sound_norm": false,
"log_func": "np.log",
"do_trim_silence": true,
"trim_db": 45,
"power": 1.5,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 0.0,
"mel_fmax": null,
"spec_gain": 1,
"do_amp_to_db_linear": false,
"do_amp_to_db_mel": true,
"signal_norm": false,
"min_level_db": -100,
"symmetric_norm": true,
"max_norm": 4.0,
"clip_norm": true,
"stats_path": null
},
"use_phonemes": false,
"use_espeak_phonemes": false,
"phoneme_language": "pt-br",
"compute_input_seq_cache": false,
"text_cleaner": "multilingual_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": {
"pad": "_",
"eos": "&",
"bos": "*",
"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' ",
"unique": true
},
"batch_group_size": 0,
"loss_masking": null,
"min_seq_len": 90,
"max_seq_len": 270,
"compute_f0": false,
"compute_linear_spec": true,
"add_blank": true,
"datasets": [
{
"name": "vctk",
"path": "../../datasets/VCTK-Corpus-removed-silence_16Khz/",
"meta_file_train": null,
"ununsed_speakers": [
"p225",
"p234",
"p238",
"p245",
"p248",
"p261",
"p294",
"p302",
"p326",
"p335",
"p347"
],
"language": "en",
"meta_file_val": null,
"meta_file_attn_mask": ""
},
{
"name": "libri_tts",
"path": "../../datasets/LibriTTS/LibriTTS/dataset-preprocessed-clean-100-and-360/dataset-22k/",
"meta_file_train": "metadata_all.csv",
"ununsed_speakers": null,
"language": "en",
"meta_file_val": "dev-clean_500.csv",
"meta_file_attn_mask": ""
},
{
"name": "brspeech",
"path": "../../datasets/TTS-Portuguese-Corpus_16khz/",
"meta_file_train": "train_TTS-Portuguese_Corpus_metadata.csv",
"ununsed_speakers": null,
"language": "pt-br",
"meta_file_val": "eval_TTS-Portuguese_Corpus_metadata.csv",
"meta_file_attn_mask": ""
},
{
"name": "mailabs",
"path": "../../datasets/M-AILABS/fr_FR",
"meta_file_train": "",
"ununsed_speakers": null,
"language": "fr-fr",
"meta_file_val": null,
"meta_file_attn_mask": null
}
],
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.8,
0.99
],
"eps": 1e-09,
"weight_decay": 0.01
},
"lr_scheduler": "",
"lr_scheduler_params": null,
"test_sentences": [
[
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
"VCTK_p225",
null,
"en"
],
[
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
"ED",
null,
"en"
],
[
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
"bernard",
null,
"en"
],
[
"This cake is great. It's so delicious and moist.",
"VCTK_p234",
null,
"en"
],
[
"This cake is great. It's so delicious and moist.",
"ED",
null,
"en"
],
[
"This cake is great. It's so delicious and moist.",
"ezwa",
null,
"en"
],
[
"Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
"ED",
null,
"pt-br"
],
[
"Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
"VCTK_p238",
null,
"pt-br"
],
[
"Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
"gilles_g_le_blanc",
null,
"pt-br"
],
[
"Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
"ED",
null,
"pt-br"
],
[
"Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
"VCTK_p245",
null,
"pt-br"
],
[
"Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
"nadine_eckert_boulet",
null,
"pt-br"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"VCTK_p245",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"ED",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"ezwa",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"bernard",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"gilles_g_le_blanc",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"nadine_eckert_boulet",
null,
"fr-fr"
],
[
"Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
"zeckou",
null,
"fr-fr"
]
],
"use_speaker_embedding": true,
"use_d_vector_file": true,
"d_vector_dim": 512,
"model_args": {
"num_chars": 165,
"out_channels": 513,
"spec_segment_size": 62,
"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": 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
],
"use_sdp": true,
"noise_scale": 1.0,
"inference_noise_scale": 0.667,
"length_scale": 1,
"noise_scale_dp": 1.0,
"inference_noise_scale_dp": 0.8,
"max_inference_len": null,
"init_discriminator": true,
"use_spectral_norm_disriminator": false,
"use_speaker_embedding": true,
"num_speakers": 1244,
"speakers_file": null,
"d_vector_file": "../speaker_embeddings/new-SE/VCTK-LibriTTS+TTS-PT+MAILABS-FR/speakers.json",
"speaker_embedding_channels": 512,
"use_d_vector_file": true,
"d_vector_dim": 512,
"detach_dp_input": true,
"use_language_embedding": true,
"embedded_language_dim": 4,
"num_languages": 3,
"use_speaker_encoder_as_loss": true,
"speaker_encoder_config_path": "../checkpoints/Speaker_Encoder/Resnet-original-paper/config.json",
"speaker_encoder_model_path": "../checkpoints/Speaker_Encoder/Resnet-original-paper/converted_checkpoint.pth.tar",
"fine_tuning_mode": 0,
"freeze_encoder": false,
"freeze_DP": false,
"freeze_PE": false,
"freeze_flow_decoder": false,
"freeze_waveform_decoder": false
},
"grad_clip": [
5.0,
5.0
],
"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,
"r": 1
}