| # susurro v2 — inference config (architecture + utility-net asset paths). | |
| # Asset paths are relative to ./styletts2/ ; infer.py resolves them. | |
| F0_path: "Utils/JDC/bst.t7" | |
| ASR_config: "Utils/ASR/config.yml" | |
| ASR_path: "Utils/ASR/epoch_00080.pth" | |
| PLBERT_dir: "Utils/PLBERT/" | |
| preprocess_params: | |
| sr: 24000 | |
| spect_params: | |
| n_fft: 2048 | |
| win_length: 1200 | |
| hop_length: 300 | |
| model_params: | |
| multispeaker: true | |
| dim_in: 64 | |
| hidden_dim: 512 | |
| max_conv_dim: 512 | |
| n_layer: 3 | |
| n_mels: 80 | |
| n_token: 178 # misaki/Kokoro phoneme vocabulary | |
| max_dur: 50 | |
| style_dim: 128 # voicepack = [acoustic(128) ; prosodic(128)] | |
| dropout: 0.2 | |
| decoder: | |
| type: 'istftnet' | |
| resblock_kernel_sizes: [3, 7, 11] | |
| upsample_rates: [10, 6] | |
| upsample_initial_channel: 512 | |
| resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]] | |
| upsample_kernel_sizes: [20, 12] | |
| gen_istft_n_fft: 20 | |
| gen_istft_hop_size: 5 | |
| slm: | |
| model: 'microsoft/wavlm-base-plus' | |
| sr: 16000 | |
| hidden: 768 | |
| nlayers: 13 | |
| initial_channel: 64 | |
| diffusion: | |
| embedding_mask_proba: 0.1 | |
| transformer: | |
| num_layers: 3 | |
| num_heads: 8 | |
| head_features: 64 | |
| multiplier: 2 | |
| dist: | |
| sigma_data: 0.2 | |
| estimate_sigma_data: true | |
| mean: -3.0 | |
| std: 1.0 | |