{ "train": { "log_interval": 200, "eval_interval": 20000, "seed": 42, "epochs": 1000, "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": true, "freeze_ZH_bert": false, "freeze_JP_bert": false, "freeze_EN_bert": false, "freeze_emo": false }, "data": { "training_files": "Data/BangDream/filelists/train.list", "validation_files": "Data/BangDream/filelists/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": 75, "cleaned_text": true, "spk2id": { "紗夜": 0, "有咲": 1, "たえ": 2, "りみ": 3, "香澄": 4, "ロック": 5, "パレオ": 6, "レイヤ": 7, "千聖": 8, "イヴ": 9, "蘭": 10, "巴": 11, "ひまり": 12, "つぐみ": 13, "華戀": 14, "晶": 15, "光": 16, "未知留": 17, "香子": 18, "雙葉": 19, "真晝": 20, "艾露": 21, "珠緒": 22, "艾露露": 23, "純那": 24, "克洛迪娜": 25, "真矢": 26, "奈奈": 27, "壘": 28, "文": 29, "一愛": 30, "菈樂菲": 31, "司": 32, "美空": 33, "靜羽": 34, "悠悠子": 35, "八千代": 36, "栞": 37, "美帆": 38, "安德露": 39, "瑪莉亞貝菈": 40, "克拉迪亞": 41, "桃樂西": 42, "瑪麗安": 43, "花音": 44, "はぐみ": 45, "こころ": 46, "美咲": 47, "沙綾": 48, "つくし": 49, "瑠唯": 50, "透子": 51, "七深": 52, "ましろ": 53, "友希那": 54, "リサ": 55, "あこ": 56, "チュチュ": 57, "薫": 58, "麻弥": 59, "彩": 60, "日菜": 61, "愛音": 62, "楽奈": 63, "そよ": 64, "立希": 65, "燐子": 66, "モカ": 67, "燈": 68, "ますき": 69, "祥子": 70, "睦": 71, "海鈴": 72, "にゃむ": 73, "初華": 74 } }, "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": "2.4" }