{ "output_path": "/apps/tts/data/output/", "logger_uri": null, "run_name": "glow_tts_ljspeech_es", "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": 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, "distributed_backend": "nccl", "distributed_url": "tcp://localhost:54321", "mixed_precision": false, "epochs": 1000, "batch_size": 32, "eval_batch_size": 16, "grad_clip": 5.0, "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": "glow_tts", "num_loader_workers": 4, "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.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": 0.0, "mel_fmax": null, "spec_gain": 20, "do_amp_to_db_linear": true, "do_amp_to_db_mel": true, "pitch_fmax": 640.0, "pitch_fmin": 0.0, "signal_norm": true, "min_level_db": -100, "symmetric_norm": true, "max_norm": 4.0, "clip_norm": true, "stats_path": null }, "use_phonemes": true, "phonemizer": "espeak", "phoneme_language": "es", "compute_input_seq_cache": false, "text_cleaner": "phoneme_cleaners", "enable_eos_bos_chars": false, "test_sentences_file": "", "phoneme_cache_path": "/apps/tts/data/output/phoneme_cache_ljspeech_es", "characters": { "characters_class": "TTS.tts.models.vits.VitsCharacters", "vocab_dict": null, "pad": "", "eos": "", "bos": "", "blank": "", "characters": "!\u00a1'(),-.:;\u00bf?abcdefghijklmnopqrstuvwxyz\u00b5\u00df\u00e0\u00e1\u00e2\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f6\u00f9\u00fa\u00fb\u00fc\u0105\u0107\u0119\u0142\u0144\u0153\u015b\u015f\u017a\u017c\u0192\u0410\u0411\u0412\u0413\u0414\u0415\u0416\u0417\u0418\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u042d\u042e\u042f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0401\u0454\u0456\u0457\u0491\u04e7 \u00ab\u00b0\u00b1\u00b5\u00bb$%&\u2018\u2019\u201a\u201c`\u201d\u201e", "punctuations": "!\u00a1'(),-.:;\u00bf? \u02d0", "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, "sort_by_audio_len": false, "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": 80, "start_by_longest": false, "datasets": [ { "name": "ljspeech", "path": "/apps/tts/data/es_ES/resampled/female/karen_savage/angelina/", "meta_file_train": "metadata.csv", "ignored_speakers": null, "language": "", "meta_file_val": "", "meta_file_attn_mask": "" } ], "test_sentences": [], "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, "num_chars": 290, "encoder_type": "rel_pos_transformer", "encoder_params": { "kernel_size": 3, "dropout_p": 0.1, "num_layers": 6, "num_heads": 2, "hidden_channels_ffn": 768, "input_length": null }, "use_encoder_prenet": true, "hidden_channels_enc": 192, "hidden_channels_dec": 192, "hidden_channels_dp": 256, "dropout_p_dp": 0.1, "dropout_p_dec": 0.05, "mean_only": true, "out_channels": 80, "num_flow_blocks_dec": 12, "inference_noise_scale": 0.0, "kernel_size_dec": 5, "dilation_rate": 1, "num_block_layers": 4, "num_speakers": 0, "c_in_channels": 0, "num_splits": 4, "num_squeeze": 2, "sigmoid_scale": false, "d_vector_dim": 0, "data_dep_init_steps": 10, "style_wav_for_test": null, "length_scale": 1.0, "use_speaker_embedding": false, "speakers_file": null, "use_d_vector_file": false, "d_vector_file": false, "min_seq_len": 3, "max_seq_len": 500, "r": 1, "github_branch": "* dev" }