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.
190 lines
6.0 KiB
190 lines
6.0 KiB
2 years ago
|
{
|
||
|
|
"output_path": "/home/cryptogoth/src/tts-training/tacotron",
|
||
|
|
"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": false,
|
||
|
|
"test_delay_epochs": -1,
|
||
|
|
"run_eval": true,
|
||
|
|
"run_eval_steps": null,
|
||
|
|
"distributed_backend": "nccl",
|
||
|
|
"distributed_url": "tcp://localhost:54321",
|
||
|
|
"mixed_precision": true,
|
||
|
|
"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": 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": 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": 1.0,
|
||
|
|
"signal_norm": true,
|
||
|
|
"min_level_db": -100,
|
||
|
|
"symmetric_norm": true,
|
||
|
|
"max_norm": 4.0,
|
||
|
|
"clip_norm": true,
|
||
|
|
"stats_path": null
|
||
|
|
},
|
||
|
|
"use_phonemes": true,
|
||
|
|
"phonemizer": "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": "/home/cryptogoth/src/tts-training/tacotron/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": null,
|
||
|
|
"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": "",
|
||
|
|
"path": "/home/cryptogoth/src/tts-training/tacotron/../datasets/LJSpeech-1.1/",
|
||
|
|
"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,
|
||
|
|
"num_chars": 131,
|
||
|
|
"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": "inside_docker"
|
||
|
|
}
|