TTS/recipes/kokoro/tacotron2-DDC/tacotron2-DDC.json

{
    "datasets": [
        {
            "formatter": "kokoro",
            "path": "DEFINE THIS",
            "meta_file_train": "metadata.csv",
            "meta_file_val": null
        }
    ],
    "audio": {
        "fft_size": 1024,
        "win_length": 1024,
        "hop_length": 256,
        "frame_length_ms": null,
        "frame_shift_ms": null,
        "sample_rate": 22050,
        "preemphasis": 0.0,
        "ref_level_db": 20,
        "do_trim_silence": true,
        "trim_db": 60,
        "power": 1.5,
        "griffin_lim_iters": 60,
        "num_mels": 80,
        "mel_fmin": 50.0,
        "mel_fmax": 7600.0,
        "spec_gain": 1,
        "signal_norm": true,
        "min_level_db": -100,
        "symmetric_norm": true,
        "max_norm": 4.0,
        "clip_norm": true,
        "stats_path": "scale_stats.npy"
    },
    "gst":{
        "gst_style_input": null,



        "gst_embedding_dim": 512,
        "gst_num_heads": 4,
        "gst_style_tokens": 10,
        "gst_use_speaker_embedding": false
	},
    "model": "Tacotron2",
    "run_name": "kokoro-ddc",
    "run_description": "tacotron2 with DDC and differential spectral loss.",
    "batch_size": 32,
    "eval_batch_size": 16,
    "mixed_precision": true,
    "distributed": {
        "backend": "nccl",
        "url": "tcp:\/\/localhost:54321"
    },
    "reinit_layers": [],
    "loss_masking": true,
    "decoder_loss_alpha": 0.5,
    "postnet_loss_alpha": 0.25,
    "postnet_diff_spec_alpha": 0.25,
    "decoder_diff_spec_alpha": 0.25,
    "decoder_ssim_alpha": 0.5,
    "postnet_ssim_alpha": 0.25,
    "ga_alpha": 5.0,
    "stopnet_pos_weight": 15.0,
    "run_eval": true,
    "test_delay_epochs": 10,
    "test_sentences_file": null,
    "noam_schedule": false,
    "grad_clip": 1.0,
    "epochs": 1000,
    "lr": 0.0001,
    "wd": 0.000001,
    "warmup_steps": 4000,
    "seq_len_norm": false,
    "memory_size": -1,
    "prenet_type": "original",
    "prenet_dropout": true,
    "attention_type": "original",
    "windowing": false,
    "use_forward_attn": false,
    "forward_attn_mask": false,
    "transition_agent": false,
    "location_attn": true,
    "bidirectional_decoder": false,
    "double_decoder_consistency": true,
    "ddc_r": 7,
    "attention_heads": 4,
    "attention_norm": "sigmoid",
    "r": 7,
    "gradual_training": [[0, 7, 64], [1, 5, 64], [50000, 3, 32], [130000, 2, 32], [290000, 1, 32]],
    "stopnet": true,
    "separate_stopnet": true,
    "print_step": 25,
    "tb_plot_step": 100,
    "print_eval": false,
    "save_step": 10000,
    "checkpoint": true,
    "keep_all_best": false,
    "keep_after": 10000,
    "tb_model_param_stats": false,
    "text_cleaner": "basic_cleaners",
    "enable_eos_bos_chars": false,
    "num_loader_workers": 4,
    "num_val_loader_workers": 4,
    "batch_group_size": 4,
    "min_seq_len": 6,
    "max_seq_len": 153,
    "compute_input_seq_cache": false,
    "use_noise_augment": true,
    "output_path": "DEFINE THIS",
    "phoneme_cache_path": "DEFINE THIS",
    "use_phonemes": true,
    "phoneme_language": "ja-jp",
    "characters": {
        "pad": "_",
        "eos": "~",
        "bos": "^",
        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
        "punctuations": "!'(),-.:;? ",
        "phonemes": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
    },
    "use_speaker_embedding": false,
    "use_gst": false,
    "use_external_speaker_embedding_file": false,
    "external_speaker_embedding_file": "../../speakers-vctk-en.json"
}