| { | |
| "output_path": "/content/drive/MyDrive/TTS/recipes/ljspeech/tacotron2-DCA/", | |
| "logger_uri": null, | |
| "run_name": "tobi-ddc", | |
| "project_name": null, | |
| "run_description": "tacotron2 with DCA", | |
| "print_step": 100, | |
| "plot_step": 100, | |
| "model_param_stats": false, | |
| "wandb_entity": null, | |
| "dashboard_logger": "tensorboard", | |
| "log_model_step": 10000, | |
| "save_step": 1000, | |
| "save_n_checkpoints": 5, | |
| "save_checkpoints": true, | |
| "save_all_best": false, | |
| "save_best_after": 10000, | |
| "target_loss": null, | |
| "print_eval": false, | |
| "test_delay_epochs": 10, | |
| "run_eval": true, | |
| "run_eval_steps": null, | |
| "distributed_backend": "nccl", | |
| "distributed_url": "tcp://localhost:54321", | |
| "mixed_precision": false, | |
| "epochs": 1000, | |
| "batch_size": 32, | |
| "eval_batch_size": 16, | |
| "grad_clip": 0.05, | |
| "scheduler_after_epoch": true, | |
| "lr": 0.001, | |
| "optimizer": "RAdam", | |
| "optimizer_params": { | |
| "betas": [ | |
| 0.9, | |
| 0.998 | |
| ], | |
| "weight_decay": 1e-06 | |
| }, | |
| "lr_scheduler": "NoamLR", | |
| "lr_scheduler_params": { | |
| "warmup_steps": 4000 | |
| }, | |
| "use_grad_scaler": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": false, | |
| "training_seed": 54321, | |
| "model": "Tacotron2", | |
| "num_loader_workers": 4, | |
| "num_eval_loader_workers": 0, | |
| "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": 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" | |
| }, | |
| "use_phonemes": false, | |
| "phonemizer": null, | |
| "phoneme_language": "vi", | |
| "compute_input_seq_cache": false, | |
| "text_cleaner": "basic_cleaners", | |
| "enable_eos_bos_chars": false, | |
| "test_sentences_file": null, | |
| "phoneme_cache_path": "DEFINE THIS", | |
| "characters": { | |
| "characters_class": "TTS.tts.utils.text.characters.Graphemes", | |
| "vocab_dict": null, | |
| "pad": "<pad>", | |
| "eos": "<eos>", | |
| "bos": "<bos>", | |
| "blank": "<blnk>", | |
| "characters": "0123456789a\u00e1\u1ea3\u00e0\u00e3\u1ea1\u00e2\u1ea5\u1ea9\u1ea7\u1eab\u1ead\u0103\u1eaf\u1eb3\u1eb1\u1eb5\u1eb7bcd\u0111e\u00e9\u1ebb\u00e8\u1ebd\u1eb9\u00ea\u1ebf\u1ec3\u1ec1\u1ec5\u1ec7fghi\u00ed\u1ec9\u00ec\u0129\u1ecbjklmno\u00f3\u1ecf\u00f2\u00f5\u1ecd\u00f4\u1ed1\u1ed5\u1ed3\u1ed7\u1ed9\u01a1\u1edb\u1edf\u1edd\u1ee1\u1ee3pqrstu\u00fa\u1ee7\u00f9\u0169\u1ee5\u01b0\u1ee9\u1eed\u1eeb\u1eef\u1ef1vwxy\u00fd\u1ef7\u1ef3\u1ef9\u1ef5z", | |
| "punctuations": "!'(),-.:;? ", | |
| "phonemes": null, | |
| "is_unique": true, | |
| "is_sorted": true | |
| }, | |
| "add_blank": false, | |
| "batch_group_size": 4, | |
| "loss_masking": true, | |
| "min_audio_len": 1, | |
| "max_audio_len": Infinity, | |
| "min_text_len": 1, | |
| "max_text_len": Infinity, | |
| "compute_f0": false, | |
| "compute_linear_spec": false, | |
| "precompute_num_workers": 0, | |
| "start_by_longest": false, | |
| "datasets": [ | |
| { | |
| "formatter": "infore22", | |
| "dataset_name": "", | |
| "path": "/content/drive/MyDrive/infore/", | |
| "meta_file_train": "scripts.csv", | |
| "ignored_speakers": null, | |
| "language": "", | |
| "meta_file_val": null, | |
| "meta_file_attn_mask": "" | |
| } | |
| ], | |
| "test_sentences": [ | |
| "T\u00f4i y\u00eau Vi\u1ec7t Nam, \u0111\u1ea5t n\u01b0\u1edbc v\u00f4 c\u00f9ng xinh \u0111\u1eb9p.", | |
| "\u0110\u1ec3 \u0111\u00e1p \u1ee9ng nhu c\u1ea7u s\u1ea3n xu\u1ea5t, T\u1eadp \u0111o\u00e0n may th\u00eau Thu\u1eadn Ph\u01b0\u01a1ng \u1edf qu\u1eadn.", | |
| "\u0110\u00e3 h\u01a1n hai l\u1ea7n nh\u00e2n vi\u00ean tuy\u1ec3n d\u1ee5ng \u0111\u1ebfn t\u1eadn nh\u00e0 m\u00e1y, c\u00e1c khu tr\u1ecd c\u00f3 c\u00f4ng nh\u00e2n T\u1ef7 H\u00f9ng \u1edf \u0111\u1ec3 g\u1eb7p g\u1ee1." | |
| ], | |
| "eval_split_max_size": null, | |
| "eval_split_size": 0.05, | |
| "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, | |
| "use_gst": false, | |
| "gst": { | |
| "gst_style_input_wav": null, | |
| "gst_style_input_weights": null, | |
| "gst_embedding_dim": 512, | |
| "gst_use_speaker_embedding": false, | |
| "gst_num_heads": 4, | |
| "gst_num_style_tokens": 10 | |
| }, | |
| "gst_style_input": null, | |
| "use_capacitron_vae": false, | |
| "capacitron_vae": null, | |
| "num_speakers": 1, | |
| "num_chars": 118, | |
| "r": 2, | |
| "gradual_training": null, | |
| "memory_size": -1, | |
| "prenet_type": "original", | |
| "prenet_dropout": true, | |
| "prenet_dropout_at_inference": false, | |
| "stopnet": true, | |
| "separate_stopnet": true, | |
| "stopnet_pos_weight": 15.0, | |
| "max_decoder_steps": 1000, | |
| "encoder_in_features": 512, | |
| "decoder_in_features": 512, | |
| "decoder_output_dim": 80, | |
| "out_channels": 80, | |
| "attention_type": "dynamic_convolution", | |
| "attention_heads": null, | |
| "attention_norm": "sigmoid", | |
| "attention_win": false, | |
| "windowing": false, | |
| "use_forward_attn": false, | |
| "forward_attn_mask": false, | |
| "transition_agent": false, | |
| "location_attn": true, | |
| "bidirectional_decoder": false, | |
| "double_decoder_consistency": true, | |
| "ddc_r": 6, | |
| "speakers_file": null, | |
| "use_speaker_embedding": false, | |
| "speaker_embedding_dim": 512, | |
| "use_d_vector_file": false, | |
| "d_vector_file": false, | |
| "d_vector_dim": null, | |
| "seq_len_norm": false, | |
| "decoder_loss_alpha": 0.25, | |
| "postnet_loss_alpha": 0.25, | |
| "postnet_diff_spec_alpha": 0.25, | |
| "decoder_diff_spec_alpha": 0.25, | |
| "decoder_ssim_alpha": 0.25, | |
| "postnet_ssim_alpha": 0.25, | |
| "ga_alpha": 5.0, | |
| "restore_path": "/content/drive/MyDrive/TTS/recipes/ljspeech/tacotron2-DCA/tobi-ddc-January-04-2023_08+44AM-3191c5f/checkpoint_95000.pth", | |
| "github_branch": "inside_docker" | |
| } |