commonvoice_be_tts_female_1 / vocoder_config.json
slapula's picture
initial commit
f091ed4
{
"output_path": "/output/vocoder",
"logger_uri": null,
"run_name": "run",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 50,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"save_on_interrupt": true,
"log_model_step": null,
"save_step": 5000,
"save_n_checkpoints": 2,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 5000,
"target_loss": "loss_0",
"print_eval": true,
"test_delay_epochs": 5,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": false,
"precision": "fp16",
"epochs": 1000,
"batch_size": 74,
"eval_batch_size": 16,
"grad_clip": [
5,
5
],
"scheduler_after_epoch": true,
"lr": 0.0001,
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.8,
0.99
],
"weight_decay": 0.0
},
"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": "hifigan",
"num_loader_workers": 8,
"num_eval_loader_workers": 8,
"use_noise_augment": true,
"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": 0.0,
"ref_level_db": 20,
"do_sound_norm": false,
"log_func": "np.log10",
"do_trim_silence": true,
"trim_db": 45,
"do_rms_norm": false,
"db_level": null,
"power": 1.5,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 50,
"mel_fmax": 8000,
"spec_gain": 20,
"do_amp_to_db_linear": true,
"do_amp_to_db_mel": true,
"pitch_fmax": 640.0,
"pitch_fmin": 1.0,
"signal_norm": true,
"min_level_db": -100,
"symmetric_norm": true,
"max_norm": 4.0,
"clip_norm": true,
"stats_path": "scale_stats_female_1.npy"
},
"eval_split_size": 30,
"data_path": "/output/dataset/female_1",
"feature_path": null,
"seq_len": 8192,
"pad_short": 2000,
"conv_pad": 0,
"use_cache": false,
"wd": 1e-06,
"use_stft_loss": false,
"use_subband_stft_loss": false,
"use_mse_gan_loss": true,
"use_hinge_gan_loss": false,
"use_feat_match_loss": true,
"use_l1_spec_loss": true,
"stft_loss_weight": 0,
"subband_stft_loss_weight": 0,
"mse_G_loss_weight": 1,
"hinge_G_loss_weight": 0,
"feat_match_loss_weight": 108,
"l1_spec_loss_weight": 45,
"stft_loss_params": {
"n_ffts": [
1024,
2048,
512
],
"hop_lengths": [
120,
240,
50
],
"win_lengths": [
600,
1200,
240
]
},
"l1_spec_loss_params": {
"use_mel": true,
"sample_rate": 22050,
"n_fft": 1024,
"hop_length": 256,
"win_length": 1024,
"n_mels": 80,
"mel_fmin": 0.0,
"mel_fmax": null
},
"lr_gen": 0.0002,
"lr_disc": 0.0002,
"lr_scheduler_gen": "ExponentialLR",
"lr_scheduler_gen_params": {
"gamma": 0.999,
"last_epoch": -1
},
"lr_scheduler_disc": "ExponentialLR",
"lr_scheduler_disc_params": {
"gamma": 0.999,
"last_epoch": -1
},
"use_pqmf": false,
"diff_samples_for_G_and_D": false,
"discriminator_model": "hifigan_discriminator",
"generator_model": "hifigan_generator",
"generator_model_params": {
"upsample_factors": [
8,
8,
2,
2
],
"upsample_kernel_sizes": [
16,
16,
4,
4
],
"upsample_initial_channel": 512,
"resblock_kernel_sizes": [
3,
7,
11
],
"resblock_dilation_sizes": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"resblock_type": "1"
},
"github_branch": "* dev"
}