| { | |
| "output_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch", | |
| "logger_uri": null, | |
| "run_name": "fast_pitch_ljspeech", | |
| "project_name": null, | |
| "run_description": "", | |
| "print_step": 50, | |
| "plot_step": 100, | |
| "model_param_stats": false, | |
| "wandb_entity": null, | |
| "dashboard_logger": "tensorboard", | |
| "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": 10000, | |
| "target_loss": null, | |
| "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, | |
| "precision": "fp16", | |
| "epochs": 1000, | |
| "batch_size": 32, | |
| "eval_batch_size": 16, | |
| "grad_clip": 5.0, | |
| "scheduler_after_epoch": false, | |
| "lr": 0.0001, | |
| "optimizer": "Adam", | |
| "optimizer_params": { | |
| "betas": [ | |
| 0.9, | |
| 0.998 | |
| ], | |
| "weight_decay": 1e-06 | |
| }, | |
| "lr_scheduler": "NoamLR", | |
| "lr_scheduler_params": { | |
| "warmup_steps": 4000 | |
| }, | |
| "use_grad_scaler": false, | |
| "allow_tf32": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": true, | |
| "training_seed": 54321, | |
| "model": "fast_pitch", | |
| "num_loader_workers": 8, | |
| "num_eval_loader_workers": 4, | |
| "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.log", | |
| "do_trim_silence": true, | |
| "trim_db": 23, | |
| "do_rms_norm": false, | |
| "db_level": null, | |
| "power": 1.5, | |
| "griffin_lim_iters": 60, | |
| "num_mels": 80, | |
| "mel_fmin": 0.0, | |
| "mel_fmax": 8000.0, | |
| "spec_gain": 1, | |
| "do_amp_to_db_linear": true, | |
| "do_amp_to_db_mel": true, | |
| "pitch_fmax": 640.0, | |
| "pitch_fmin": 0.0, | |
| "signal_norm": false, | |
| "min_level_db": -100, | |
| "symmetric_norm": true, | |
| "max_norm": 4.0, | |
| "clip_norm": true, | |
| "stats_path": null | |
| }, | |
| "use_phonemes": true, | |
| "phonemizer": "gruut", | |
| "phoneme_language": "en-us", | |
| "compute_input_seq_cache": true, | |
| "text_cleaner": "english_cleaners", | |
| "enable_eos_bos_chars": false, | |
| "test_sentences_file": "", | |
| "phoneme_cache_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch/phoneme_cache", | |
| "characters": { | |
| "characters_class": null, | |
| "vocab_dict": null, | |
| "pad": "_", | |
| "eos": "~", | |
| "bos": "^", | |
| "blank": null, | |
| "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ", | |
| "punctuations": "!'(),-.:;? ", | |
| "phonemes": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b", | |
| "is_unique": true, | |
| "is_sorted": true | |
| }, | |
| "add_blank": false, | |
| "batch_group_size": 0, | |
| "loss_masking": null, | |
| "min_audio_len": 1, | |
| "max_audio_len": Infinity, | |
| "min_text_len": 1, | |
| "max_text_len": Infinity, | |
| "compute_f0": true, | |
| "compute_energy": false, | |
| "compute_linear_spec": false, | |
| "precompute_num_workers": 0, | |
| "start_by_longest": false, | |
| "shuffle": false, | |
| "drop_last": false, | |
| "datasets": [ | |
| { | |
| "formatter": "", | |
| "dataset_name": "", | |
| "path": "/home/ubuntu/TTS/VCTK-Corpus-removed-silence", | |
| "meta_file_train": "", | |
| "ignored_speakers": null, | |
| "language": "", | |
| "phonemizer": "", | |
| "meta_file_val": "", | |
| "meta_file_attn_mask": "" | |
| } | |
| ], | |
| "test_sentences": [ | |
| "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.", | |
| "Be a voice, not an echo.", | |
| "I'm sorry Dave. I'm afraid I can't do that.", | |
| "This cake is great. It's so delicious and moist.", | |
| "Prior to November 22, 1963." | |
| ], | |
| "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, | |
| "base_model": "forward_tts", | |
| "model_args": { | |
| "num_chars": 130, | |
| "out_channels": 80, | |
| "hidden_channels": 384, | |
| "use_aligner": true, | |
| "use_pitch": true, | |
| "pitch_predictor_hidden_channels": 256, | |
| "pitch_predictor_kernel_size": 3, | |
| "pitch_predictor_dropout_p": 0.1, | |
| "pitch_embedding_kernel_size": 3, | |
| "use_energy": false, | |
| "energy_predictor_hidden_channels": 256, | |
| "energy_predictor_kernel_size": 3, | |
| "energy_predictor_dropout_p": 0.1, | |
| "energy_embedding_kernel_size": 3, | |
| "duration_predictor_hidden_channels": 256, | |
| "duration_predictor_kernel_size": 3, | |
| "duration_predictor_dropout_p": 0.1, | |
| "positional_encoding": true, | |
| "poisitonal_encoding_use_scale": true, | |
| "length_scale": 1, | |
| "encoder_type": "fftransformer", | |
| "encoder_params": { | |
| "hidden_channels_ffn": 1024, | |
| "num_heads": 1, | |
| "num_layers": 6, | |
| "dropout_p": 0.1 | |
| }, | |
| "decoder_type": "fftransformer", | |
| "decoder_params": { | |
| "hidden_channels_ffn": 1024, | |
| "num_heads": 1, | |
| "num_layers": 6, | |
| "dropout_p": 0.1 | |
| }, | |
| "detach_duration_predictor": false, | |
| "max_duration": 75, | |
| "num_speakers": 108, | |
| "use_speaker_embedding": true, | |
| "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--fast_pitch/speaker_ids.json", | |
| "use_d_vector_file": false, | |
| "d_vector_dim": 0, | |
| "d_vector_file": null | |
| }, | |
| "num_speakers": 0, | |
| "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--fast_pitch/speaker_ids.json", | |
| "use_speaker_embedding": true, | |
| "use_d_vector_file": false, | |
| "d_vector_file": false, | |
| "d_vector_dim": 0, | |
| "spec_loss_type": "mse", | |
| "duration_loss_type": "mse", | |
| "use_ssim_loss": true, | |
| "ssim_loss_alpha": 1.0, | |
| "spec_loss_alpha": 1.0, | |
| "aligner_loss_alpha": 1.0, | |
| "pitch_loss_alpha": 1.0, | |
| "dur_loss_alpha": 1.0, | |
| "binary_align_loss_alpha": 1.0, | |
| "binary_loss_warmup_epochs": 150, | |
| "min_seq_len": 13, | |
| "max_seq_len": 500000, | |
| "r": 1, | |
| "f0_cache_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch/f0_cache" | |
| } |