You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

198 lines
6.2 KiB

{
"output_path": "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": 10000,
"save_n_checkpoints": 5,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 10000,
"target_loss": null,
"print_eval": true,
"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": 5.0,
"scheduler_after_epoch": true,
"lr": 0.0001,
"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": 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": 60.0,
"do_rms_norm": false,
"db_level": null,
"power": 1.5,
"griffin_lim_iters": 60,
"num_mels": 80,
"mel_fmin": 0.0,
"mel_fmax": 8000,
"spec_gain": 1.0,
"do_amp_to_db_linear": true,
"do_amp_to_db_mel": true,
"pitch_fmax": 640.0,
"pitch_fmin": 1.0,
"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": false,
"text_cleaner": "phoneme_cleaners",
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": "output/phoneme_cache",
"characters": {
"characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
"vocab_dict": null,
"pad": "<PAD>",
"eos": "<EOS>",
"bos": "<BOS>",
"blank": "<BLNK>",
"characters": "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",
"punctuations": "!'(),-.:;? ",
"phonemes": null,
"is_unique": false,
"is_sorted": true
},
"add_blank": false,
"batch_group_size": 0,
"loss_masking": true,
"min_audio_len": 1,
"max_audio_len": Infinity,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": false,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "ljspeech",
"dataset_name": "ljspeech",
"path": "output",
"meta_file_train": "metadata.csv",
"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,
"use_gst": false,
"gst": null,
"gst_style_input": null,
"use_capacitron_vae": false,
"capacitron_vae": null,
"num_speakers": 1,
"num_chars": 131,
"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": 0.2,
"max_decoder_steps": 10000,
"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": false,
"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,
"decoder_diff_spec_alpha": 0,
"decoder_ssim_alpha": 0,
"postnet_ssim_alpha": 0,
"ga_alpha": 0.0,
"github_branch": "* main"
}