{ "train": { "log_interval": 200, "eval_interval": 10000, "save_interval": 10000, "seed": 1234, "epochs": 20000, "learning_rate": 2e-4, "betas": [0.8, 0.99], "eps": 1e-9, "batch_size": 16, "fp16_run": false, "lr_decay": 0.999875, "segment_size": 16640, "init_lr_ratio": 1, "warmup_epochs": 0, "c_mel": 45, "c_kl": 1, "c_kl_pitch": 1, "c_pho": 45.0, "fs": true, "lambda_commit": 0.02 }, "data": { "train_filelist_path": "filelists/train_f0_final.txt", "test_filelist_path": "filelists/test_f0_final.txt", "text_cleaners":["english_cleaners2"], "max_wav_value": 32768.0, "sampling_rate": 16000, "filter_length": 1280, "hop_length": 320, "win_length": 1280, "n_mel_channels": 80, "mel_fmin": 0, "mel_fmax": 8000, "add_blank": true, "n_speakers": 0, "cleaned_text": true, "aug_rate": 1.0, "top_db": 20 }, "model": { "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": [5,4,4,2,2], "upsample_initial_channel": 512, "upsample_kernel_sizes": [11,8,8,4,4], "mixup_ratio": 0.6, "n_layers_q": 3, "use_spectral_norm": false }, "f0_vq_params": { "l_bins": 20, "emb_width": 128, "mu": 0.99, "levels": 1 }, "f0_encoder_params": { "input_emb_width": 1, "output_emb_width": 128, "levels": 1, "downs_t": [4], "strides_t": [2], "width": 32, "depth": 4, "m_conv": 1.0, "dilation_growth_rate": 3 }, "f0_decoder_params": { "input_emb_width": 1, "output_emb_width": 128, "levels": 1, "downs_t": [4], "strides_t": [2], "width": 32, "depth": 4, "m_conv": 1.0, "dilation_growth_rate": 3 } }