{ "model_name": "visual_novel", "train": { "log_interval": 200, "eval_interval": 1000, "seed": 42, "epochs": 100, "learning_rate": 0.0001, "betas": [ 0.8, 0.99 ], "eps": 1e-09, "batch_size": 8, "bf16_run": false, "fp16_run": false, "lr_decay": 0.99996, "segment_size": 16384, "init_lr_ratio": 1, "warmup_epochs": 0, "c_mel": 45, "c_kl": 1.0, "c_commit": 100, "skip_optimizer": false, "freeze_ZH_bert": false, "freeze_JP_bert": false, "freeze_EN_bert": false, "freeze_emo": false, "freeze_style": false, "freeze_decoder": false }, "data": { "use_jp_extra": true, "training_files": "Data/visual_novel/train.list", "validation_files": "Data/visual_novel/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, "n_speakers": 16, "cleaned_text": true, "spk2id": { "あやせ": 0, "ナツメ": 1, "ムラサメ": 2, "レナ": 3, "七海": 4, "千咲": 5, "小春": 6, "希": 7, "愛衣": 8, "栞那": 9, "涼音": 10, "羽月": 11, "芦花": 12, "芳乃": 13, "茉優": 14, "茉子": 15 }, "num_styles": 17, "style2id": { "Neutral": 0, "あやせ": 1, "ナツメ": 2, "ムラサメ": 3, "レナ": 4, "七海": 5, "千咲": 6, "小春": 7, "希": 8, "愛衣": 9, "栞那": 10, "涼音": 11, "羽月": 12, "芦花": 13, "芳乃": 14, "茉優": 15, "茉子": 16 } }, "model": { "use_spk_conditioned_encoder": true, "use_noise_scaled_mas": true, "use_mel_posterior_encoder": false, "use_duration_discriminator": false, "use_wavlm_discriminator": true, "inter_channels": 192, "hidden_channels": 192, "filter_channels": 768, "n_heads": 2, "n_layers": 6, "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": 512, "slm": { "model": "./slm/wavlm-base-plus", "sr": 16000, "hidden": 768, "nlayers": 13, "initial_channel": 64 } }, "version": "2.5.0-JP-Extra" }