bel-tts / config.json
jhlfrfufyfn's picture
Update config.json
55a3ecb
{
"output_path": "/storage/output",
"logger_uri": null,
"run_name": "run",
"project_name": null,
"run_description": "\ud83d\udc38Coqui trainer run.",
"print_step": 50,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"log_model_step": null,
"save_step": 10000,
"save_n_checkpoints": 2,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 5000,
"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": 32,
"grad_clip": 5.0,
"scheduler_after_epoch": true,
"lr": 1e-05,
"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": 8,
"num_eval_loader_workers": 8,
"use_noise_augment": true,
"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": 50.0,
"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": null,
"compute_input_seq_cache": false,
"text_cleaner": "remove_aux_symbols",
"enable_eos_bos_chars": true,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": {
"characters_class": "TTS.tts.utils.text.characters.Graphemes",
"vocab_dict": null,
"pad": "_",
"eos": "~",
"bos": "^",
"blank": "@",
"characters": "\u0481\u0482\u0439\u044b\u0448\u0447\u0426\u0446\u0425\u0445\u0424\u0444\u0423\u0443\u0422\u0442\u0421\u0441\u0440\u041f\u043f\u043e\u041d\u043d\u041c\u04ce\u043c\u041b\u043b\u041a\u043a\u0456\u0417\u0437\u0499\u0495\u0496\u0497\u0435\u0414\u0434\u0413\u0433\u0490\u0491\u0475\u0412\u0432\u0411\u0431\u0430",
"punctuations": "!,.? -",
"phonemes": null,
"is_unique": true,
"is_sorted": true
},
"add_blank": true,
"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": "bel_tts_formatter",
"dataset_name": "",
"path": "/storage/filtered_dataset/",
"meta_file_train": "ipa_final_dataset.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": 61,
"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,
"restore_path": "/storage/output/run-April-30-2023_01+57AM-f9e7c410/best_model_57989.pth",
"github_branch": "* dev"
}