{ "train": { "attr_dropout_prob": 0.3, "clone_dropout_prob": 0.3, "log_interval": 200, "eval_interval": 1000, "seed": 52, "epochs": 10000, "learning_rate": 0.00002, "betas": [ 0.8, 0.99 ], "eps": 1e-09, "batch_size": 6, "fp16_run": false, "lr_decay": 0.999875, "segment_size": 16384, "init_lr_ratio": 1, "warmup_epochs": 0, "c_mel": 45, "c_kl": 1.0, "kl_warmup_steps": 800000, "grad_clip_thresh": 1.0, "skip_optimizer": true }, "data": { "training_files": "/mnt/bn/automastering-396caa4f/yt_小林说/train.list", "validation_files": "/mnt/bn/automastering-396caa4f/yt_小林说/val.list", "max_wav_value": 32768.0, "sampling_rate": 44100, "filter_length": 2048, "hop_length": 512, "win_length": 2048, "n_mel_channels": 128, "mel_fmin": 0.0, "mel_fmax": null, "add_blank": true, "cleaned_text": true }, "model": { "use_noise_scaled_mas": true, "use_mel_posterior_encoder": false, "use_duration_discriminator": true, "inter_channels": 192, "hidden_channels": 256, "filter_channels": 768, "n_heads": 2, "n_layers": 8, "n_layers_trans_flow": 3, "kernel_size": 3, "p_dropout": 0.1, "resblock": "1", "resblock_kernel_sizes": [ 3, 7, 11 ], "resblock_dilation_sizes": [ [ 1, 3, 5 ], [ 1, 3, 5 ], [ 1, 3, 5 ] ], "upsample_rates": [ 8, 8, 2, 2, 2 ], "upsample_initial_channel": 512, "upsample_kernel_sizes": [ 16, 16, 8, 2, 2 ], "n_layers_q": 3, "use_spectral_norm": false, "gin_channels": 256, "use_mamba": true }, "num_languages": 3, "num_tones": 10, "symbols": [ "_", "AA", "E", "EE", "En", "OO", "V", "a", "aa", "ae", "ah", "ai", "an", "ang", "ao", "aw", "ay", "b", "c", "ch", "d", "dh", "e", "eh", "ei", "en", "eng", "er", "ey", "f", "g", "h", "hh", "i", "i0", "ia", "ian", "iang", "iao", "ie", "ih", "in", "ing", "iong", "ir", "iu", "iy", "j", "jh", "k", "l", "m", "n", "ng", "o", "ong", "ou", "ow", "oy", "p", "q", "r", "s", "sh", "t", "th", "u", "ua", "uai", "uan", "uang", "uh", "ui", "un", "uo", "uw", "v", "van", "ve", "vn", "w", "x", "y", "z", "zh", "!", "?", "…", ",", ".", "'", "-", "¿", "¡", "SP", "UNK" ] }