{ "output_path": "/content/drive/MyDrive/TTS/recipes/ljspeech/tacotron2-DDC/univnet", "logger_uri": null, "run_name": "tobi-univnet", "project_name": null, "run_description": "", "print_step": 100, "plot_step": 100, "model_param_stats": false, "wandb_entity": null, "dashboard_logger": "tensorboard", "log_model_step": null, "save_step": 5000, "save_n_checkpoints": 5, "save_checkpoints": true, "save_all_best": false, "save_best_after": 10000, "target_loss": "loss_0", "print_eval": false, "test_delay_epochs": -1, "run_eval": true, "run_eval_steps": null, "distributed_backend": "nccl", "distributed_url": "tcp://localhost:54321", "mixed_precision": false, "epochs": 1000, "batch_size": 10, "eval_batch_size": 16, "grad_clip": null, "scheduler_after_epoch": false, "lr": 0.001, "optimizer": "AdamW", "optimizer_params": { "betas": [ 0.5, 0.9 ], "weight_decay": 0.0 }, "lr_scheduler": null, "lr_scheduler_params": {}, "use_grad_scaler": false, "cudnn_enable": true, "cudnn_deterministic": false, "cudnn_benchmark": false, "training_seed": 54321, "model": "univnet", "num_loader_workers": 2, "num_eval_loader_workers": 2, "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": 30, "do_rms_norm": false, "db_level": null, "power": 1.5, "griffin_lim_iters": 60, "num_mels": 80, "mel_fmin": 70.0, "mel_fmax": 8000.0, "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.npy" }, "eval_split_size": 10, "data_path": "/content/drive/MyDrive/infore/wav22", "feature_path": null, "seq_len": 8192, "pad_short": 2000, "conv_pad": 0, "use_cache": false, "wd": 0.0, "use_stft_loss": true, "use_subband_stft_loss": false, "use_mse_gan_loss": true, "use_hinge_gan_loss": false, "use_feat_match_loss": false, "use_l1_spec_loss": false, "stft_loss_weight": 2.5, "subband_stft_loss_weight": 0.0, "mse_G_loss_weight": 1.0, "hinge_G_loss_weight": 0.0, "feat_match_loss_weight": 0.0, "l1_spec_loss_weight": 0.0, "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": 0.0001, "lr_disc": 0.0001, "lr_scheduler_gen": null, "lr_scheduler_gen_params": { "gamma": 0.999, "last_epoch": -1 }, "lr_scheduler_disc": null, "lr_scheduler_disc_params": { "gamma": 0.999, "last_epoch": -1 }, "use_pqmf": false, "diff_samples_for_G_and_D": false, "discriminator_model": "univnet_discriminator", "generator_model": "univnet_generator", "generator_model_params": { "in_channels": 64, "out_channels": 1, "hidden_channels": 32, "cond_channels": 80, "upsample_factors": [ 8, 8, 4 ], "lvc_layers_each_block": 4, "lvc_kernel_size": 3, "kpnet_hidden_channels": 64, "kpnet_conv_size": 3, "dropout": 0.0 }, "steps_to_start_discriminator": 200000, "restore_path": "/content/drive/MyDrive/TTS/recipes/ljspeech/tacotron2-DDC/univnet/tobi-univnet-January-04-2023_04+20AM-3191c5f/checkpoint_635000.pth", "github_branch": "inside_docker" }