txya900619's picture
upload: model pth and configs
fff9519
{
"output_path": "/mnt/user_wayne/TTS/recipes/hat-tts/vits",
"logger_uri": null,
"run_name": "vits_hat_tts",
"project_name": "vits_hat_tts",
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 50,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "wandb",
"save_on_interrupt": true,
"log_model_step": 10000,
"save_step": 10000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 0,
"target_loss": null,
"print_eval": true,
"test_delay_epochs": -1,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": true,
"precision": "fp16",
"epochs": 1000,
"batch_size": 32,
"eval_batch_size": 32,
"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": null,
"lr_scheduler_params": {},
"use_grad_scaler": false,
"allow_tf32": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 54321,
"model": "vits",
"num_loader_workers": 16,
"num_eval_loader_workers": 16,
"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": null,
"phoneme_language": null,
"compute_input_seq_cache": true,
"text_cleaner": null,
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": {
"characters_class": "TTS.tts.models.vits.VitsCharacters",
"vocab_dict": null,
"pad": "<PAD>",
"eos": "<EOS>",
"bos": "<BOS>",
"blank": "<BLNK>",
"characters": [
"a",
"e",
"f",
"h",
"i",
"k",
"l",
"m",
"n",
"o",
"p",
"s",
"t",
"u",
"v",
"\u014b",
"\u0255",
"\u0259",
"\u0268",
"\u0282",
"\u0288",
"\u0290",
"\u02b0",
"\u0329",
"\u0361",
"\uff0c",
"11",
"2",
"24",
"31",
"33",
"5",
"53",
"55"
],
"punctuations": "\uff0c ",
"phonemes": null,
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"batch_group_size": 32,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": 1440000,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": true,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "hat_tts",
"dataset_name": "",
"path": "/mnt/user_wayne/hat_tts",
"meta_file_train": "sixian.json",
"ignored_speakers": null,
"language": "sixian",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
},
{
"formatter": "hat_tts",
"dataset_name": "",
"path": "/mnt/user_wayne/hat_tts",
"meta_file_train": "hailu.json",
"ignored_speakers": null,
"language": "hailu",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
[
[
"a",
"n",
"31",
"t",
"\u0361",
"s",
"o",
"31",
" ",
"\uff0c",
" ",
"s",
"\u0268",
"t",
"5",
"p",
"a",
"u",
"31",
"m",
"a",
"\u014b",
"11",
" ",
"\uff0c",
" ",
"s",
"\u0268",
"t",
"5",
"p",
"a",
"u",
"31",
" ",
"l",
"e",
"24",
" ",
"\uff0c",
" ",
"n",
"\u0329",
"11",
" ",
"\u014b",
"a",
"i",
"11",
" ",
"k",
"i",
"11",
" ",
"\uff0c",
" ",
"\u014b",
"\u0329",
"11",
"k",
"o",
"\u014b",
"31",
"m",
"a",
"31",
"k",
"e",
"55",
" ",
"\uff0c",
" ",
"n",
"\u0329",
"11",
" ",
"h",
"e",
"55",
"m",
"o",
"11",
" ",
"s",
"a",
"11",
" ",
"\uff0c",
" ",
"\u014b",
"a",
"i",
"11",
" ",
"h",
"e",
"55",
" ",
"a",
"24",
" ",
"l",
"i",
"n",
"11",
" ",
"\uff0c",
" ",
"a",
"n",
"31",
"k",
"i",
"u",
"31",
"m",
"o",
"11",
"k",
"\u02b0",
"o",
"n",
"55",
"t",
"o",
"31",
" ",
"\uff0c",
" ",
"\u014b",
"i",
"11",
"h",
"o",
"31",
" ",
"m",
"o",
"11"
],
"XF",
null,
"sixian"
],
[
[
"a",
"n",
"31",
"t",
"\u0361",
"s",
"o",
"31",
" ",
"\uff0c",
" ",
"s",
"\u0268",
"t",
"5",
"p",
"a",
"u",
"31",
"m",
"a",
"\u014b",
"11",
" ",
"\uff0c",
" ",
"s",
"\u0268",
"t",
"5",
"p",
"a",
"u",
"31",
" ",
"l",
"e",
"24",
" ",
"\uff0c",
" ",
"n",
"\u0329",
"11",
" ",
"\u014b",
"a",
"i",
"11",
" ",
"k",
"i",
"11",
" ",
"\uff0c",
" ",
"\u014b",
"\u0329",
"11",
"k",
"o",
"\u014b",
"31",
"m",
"a",
"31",
"k",
"e",
"55",
" ",
"\uff0c",
" ",
"n",
"\u0329",
"11",
" ",
"h",
"e",
"55",
"m",
"o",
"11",
" ",
"s",
"a",
"11",
" ",
"\uff0c",
" ",
"\u014b",
"a",
"i",
"11",
" ",
"h",
"e",
"55",
" ",
"a",
"24",
" ",
"l",
"i",
"n",
"11",
" ",
"\uff0c",
" ",
"a",
"n",
"31",
"k",
"i",
"u",
"31",
"m",
"o",
"11",
"k",
"\u02b0",
"o",
"n",
"55",
"t",
"o",
"31",
" ",
"\uff0c",
" ",
"\u014b",
"i",
"11",
"h",
"o",
"31",
" ",
"m",
"o",
"11"
],
"XM",
null,
"sixian"
],
[
[
"t",
"\u02b0",
"e",
"u",
"55",
"t",
"\u0361",
"s",
"\u02b0",
"i",
"e",
"n",
"55",
" ",
"v",
"a",
"t",
"5",
" ",
"\u0288",
"\u0361",
"\u0282",
"o",
"n",
"24",
" ",
"\u0288",
"\u0361",
"\u0282",
"i",
"n",
"11",
"p",
"\u02b0",
"i",
"e",
"n",
"24",
" ",
"t",
"\u0361",
"s",
"\u02b0",
"i",
"u",
"55",
" ",
"t",
"o",
"11",
" ",
"t",
"\u02b0",
"o",
"i",
"55",
"p",
"e",
"t",
"5",
" ",
"\u0282",
"i",
"33",
" ",
"\u0288",
"\u0361",
"\u0282",
"i",
"n",
"11",
"f",
"u",
"24",
" ",
"l",
"e",
"24"
],
"HF",
null,
"hailu"
],
[
[
"t",
"\u02b0",
"e",
"u",
"55",
"t",
"\u0361",
"s",
"\u02b0",
"i",
"e",
"n",
"55",
" ",
"v",
"a",
"t",
"5",
" ",
"\u0288",
"\u0361",
"\u0282",
"o",
"n",
"24",
" ",
"\u0288",
"\u0361",
"\u0282",
"i",
"n",
"11",
"p",
"\u02b0",
"i",
"e",
"n",
"24",
" ",
"t",
"\u0361",
"s",
"\u02b0",
"i",
"u",
"55",
" ",
"t",
"o",
"11",
" ",
"t",
"\u02b0",
"o",
"i",
"55",
"p",
"e",
"t",
"5",
" ",
"\u0282",
"i",
"33",
" ",
"\u0288",
"\u0361",
"\u0282",
"i",
"n",
"11",
"f",
"u",
"24",
" ",
"l",
"e",
"24"
],
"HM",
null,
"hailu"
]
],
"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": 38,
"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": 4,
"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": true,
"embedded_language_dim": 4,
"num_languages": 2,
"language_ids_file": "language_ids.json",
"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,
"use_weighted_sampler": false,
"weighted_sampler_attrs": {},
"weighted_sampler_multipliers": {},
"r": 1,
"num_speakers": 0,
"use_speaker_embedding": true,
"speakers_file": "speakers.pth",
"speaker_embedding_channels": 256,
"language_ids_file": "language_ids.json",
"use_language_embedding": true,
"use_d_vector_file": false,
"d_vector_file": null,
"d_vector_dim": 0
}