| { | |
| "output_path": "/kaggle/working/train_output", | |
| "logger_uri": null, | |
| "run_name": "run", | |
| "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": null, | |
| "save_step": 1000, | |
| "save_n_checkpoints": 5, | |
| "save_checkpoints": true, | |
| "save_all_best": false, | |
| "save_best_after": 1000, | |
| "target_loss": "loss", | |
| "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": 64, | |
| "eval_batch_size": 16, | |
| "grad_clip": 4.0, | |
| "scheduler_after_epoch": true, | |
| "lr": 0.0001, | |
| "optimizer": "AdamW", | |
| "optimizer_params": { | |
| "betas": [ | |
| 0.8, | |
| 0.99 | |
| ], | |
| "weight_decay": 0.0 | |
| }, | |
| "lr_scheduler": "MultiStepLR", | |
| "lr_scheduler_params": { | |
| "gamma": 0.5, | |
| "milestones": [ | |
| 200000, | |
| 400000, | |
| 600000 | |
| ] | |
| }, | |
| "use_grad_scaler": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": false, | |
| "training_seed": 54321, | |
| "model": "wavernn", | |
| "num_loader_workers": 1, | |
| "num_eval_loader_workers": 1, | |
| "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": 24000, | |
| "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": 95, | |
| "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": null | |
| }, | |
| "eval_split_size": 10, | |
| "data_path": "/kaggle/input/persian-tts-dataset-famale/wavs/", | |
| "feature_path": null, | |
| "seq_len": 1280, | |
| "pad_short": 2000, | |
| "conv_pad": 0, | |
| "use_cache": true, | |
| "wd": 0.0, | |
| "model_args": { | |
| "rnn_dims": 512, | |
| "fc_dims": 512, | |
| "compute_dims": 128, | |
| "res_out_dims": 128, | |
| "num_res_blocks": 10, | |
| "use_aux_net": true, | |
| "use_upsample_net": true, | |
| "upsample_factors": [ | |
| 4, | |
| 8, | |
| 8 | |
| ], | |
| "mode": "mold", | |
| "mulaw": true, | |
| "pad": 2, | |
| "feat_dims": 80 | |
| }, | |
| "batched": true, | |
| "target_samples": 11000, | |
| "overlap_samples": 550, | |
| "num_epochs_before_test": 10, | |
| "github_branch": "inside_docker" | |
| } |